name_tamer 0.6.0 → 1.0.0

data/lib/name_tamer/strings/capitalization.rb

@@ -0,0 +1,46 @@
+# frozen_string_literal: true
+
+module NameTamer
+  module Strings
+    module_function
+
+    def upcase_first_letter(string)
+      string.gsub(/\b\w/, &:upcase)
+    end
+
+    def downcase_after_apostrophe(string)
+      string.gsub(/'\w\b/, &:downcase) # Lowercase 's
+    end
+
+    # Our list of terminal characters that indicate a non-celtic name used
+    # to include o but we removed it because of MacMurdo.
+    def fix_mac(string)
+      return string unless /\bMac[A-Za-z]{2,}[^acizj]\b/.match?(string) || /\bMc/.match?(string)
+
+      fixed = string.gsub(/\b(Ma?c)([A-Za-z]+)/) { Regexp.last_match[1] + Regexp.last_match[2].capitalize }
+
+      # Fix Mac exceptions
+      MAC_EXCEPTIONS.reduce(fixed) { |name, mac_name| name.gsub(/\b#{mac_name}/, mac_name.capitalize) }
+    end
+
+    # Fix ff wierdybonks
+    def fix_ff(string)
+      FF_NAMES.reduce(string) { |name, ff_name| name.gsub(ff_name, ff_name.downcase) }
+    end
+
+    # Upcase words with no vowels, e.g JPR Williams
+    # Except Ng http://en.wikipedia.org/wiki/Ng
+    def upcase_initials(string)
+      string
+        .gsub(/\b([bcdfghjklmnpqrstvwxz]+)\b/i) { Regexp.last_match[1].upcase }
+        .gsub(/\b(NG)\b/i) { Regexp.last_match[1].capitalize }
+    end
+
+    MAC_EXCEPTIONS = %w[
+      MacEdo MacEvicius MacHado MacHar MacHin MacHlin MacIas MacIulis MacKie
+      MacKle MacKlin MacKmin MacKmurdo MacQuarie MacLise MacKenzie
+    ].freeze
+
+    FF_NAMES = %w[Fforbes Fforde Ffinch Ffrench Ffoulkes].freeze
+  end
+end

data/lib/name_tamer/strings/compound_names.rb

@@ -0,0 +1,34 @@
+# frozen_string_literal: true
+
+module NameTamer
+  module Strings
+    module_function
+
+    # Fix known last names that have spaces (not hyphens!)
+    def nbsp_in_compound_name(string)
+      COMPOUND_NAMES.reduce(string) do |name, compound_name|
+        name.gsub(compound_name, compound_name.tr(ASCII_SPACE, NONBREAKING_SPACE))
+      end
+    end
+
+    COMPOUND_NAMES = [
+      # Known families with a space in their surname
+      'Baron Cohen',
+      'Bonham Carter',
+      'Holmes a Court',
+      'Holmes à Court',
+      'Lane Fox',
+      'Lloyd Webber',
+      'Pitt Rivers',
+      'Sebag Montefiore',
+      'Strang Steel',
+      'Wedgwood Benn',
+      'Wingfield Digby',
+      # Sometimes companies appear as people
+      'Corporation Company',
+      'Corporation System',
+      'Incorporations Limited',
+      'Service Company',
+    ].freeze
+  end
+end

data/lib/name_tamer/strings/core.rb

@@ -0,0 +1,62 @@
+# frozen_string_literal: true
+
+module NameTamer
+  # Pure string transformations used throughout the gem. Every method
+  # takes a string and returns a new string; arguments are never mutated.
+  module Strings
+    module_function
+
+    def presence(string)
+      string unless string.empty?
+    end
+
+    # Change any whitespace into our separator character
+    def whitespace_to(string, separator)
+      string.gsub(/[[:space:]]+/, separator)
+    end
+
+    # Change some characters embedded in words to our separator character
+    # e.g. example.com -> example-com
+    def invalid_chars_to(string, separator)
+      string.gsub(%r{(?<![[:space:]])[./](?![[:space:]])}, separator)
+    end
+
+    # Remove HTML entities
+    def unescape_html(string)
+      CGI.unescapeHTML string
+    end
+
+    # Make sure separators are not where they shouldn't be
+    def fix_separators(string, separator)
+      return string if separator.nil? || separator.empty?
+
+      r = Regexp.escape(separator)
+
+      # No more than one separator in a row, no leading or trailing separator
+      string.gsub(/#{r}{2,}/, separator).gsub(/^#{r}|#{r}$/i, '')
+    end
+
+    def remove_periods_from_initials(string)
+      string.gsub(/\b([a-z])\./i) { Regexp.last_match[1] }
+    end
+
+    # Strip unwanted characters out completely
+    def strip_unwanted(string, filter)
+      string.gsub(filter, '')
+    end
+
+    # Unescape percent-encoded characters
+    # This might introduce UTF-8 invalid byte sequence
+    # so we take precautions
+    def safe_unescape(string)
+      unescaped = CGI.unescape(string.gsub('+', '%2B'))
+      return string if string == unescaped
+
+      ensure_safe(unescaped)
+    end
+
+    def ensure_safe(string)
+      string.encode('UTF-8', invalid: :replace, undef: :replace, replace: '')
+    end
+  end
+end

data/lib/name_tamer/strings/name_modifiers.rb

@@ -0,0 +1,51 @@
+# frozen_string_literal: true
+
+module NameTamer
+  module Strings
+    module_function
+
+    # Fixes for name modifiers followed by space
+    # Also replaces spaces with non-breaking spaces
+    # Fixes for name modifiers followed by an apostrophe,
+    # e.g. d'Artagnan, Commedia dell'Arte
+    def fix_name_modifiers(string)
+      fixed = NAME_MODIFIERS.reduce(string) do |name, modifier|
+        name.gsub(/((?:[[:space:]]|^)#{modifier})([[:space:]]+|-)/) do
+          "#{Regexp.last_match[1].rstrip.downcase}#{Regexp.last_match[2].tr(ASCII_SPACE, NONBREAKING_SPACE)}"
+        end
+      end
+
+      fix_apostrophe_modifiers(fixed)
+    end
+
+    def fix_apostrophe_modifiers(string)
+      %w[Dell D].reduce(string) do |name, modifier|
+        name.gsub(/(.#{modifier}')(\w)/) { "#{Regexp.last_match[1].rstrip.downcase}#{Regexp.last_match[2]}" }
+      end
+    end
+
+    def nbsp_in_name_modifier(string)
+      NAME_MODIFIERS.reduce(string) do |name, modifier|
+        name.gsub(/([[:space:]]#{modifier})([[:space:]])/i) { "#{Regexp.last_match[1]}#{NONBREAKING_SPACE}" }
+      end
+    end
+
+    NAME_MODIFIERS = [
+      'Al',
+      'Ap',
+      'Ben',
+      'D[aeiou]',
+      'D[ao]s',
+      'De[lrn]',
+      'Dell[ae]',
+      'El',
+      'L[eo]',
+      'La',
+      'Of',
+      'San',
+      'St[\.]?',
+      'V[ao]n',
+      'Zur',
+    ].freeze
+  end
+end

data/lib/name_tamer/strings/spacing.rb

@@ -0,0 +1,22 @@
+# frozen_string_literal: true
+
+module NameTamer
+  module Strings
+    module_function
+
+    # Ensure commas have exactly one space after them
+    def space_around_comma(string)
+      string.gsub(/[[:space:]]*,[[:space:]]*/, ', ')
+    end
+
+    def remove_spaces_from_initials(string)
+      string.gsub(/\b([a-z])(\.)* \b(?![a-z0-9'À-ÿ]{2,})/i) do
+        "#{Regexp.last_match[1]}#{Regexp.last_match[2]}"
+      end
+    end
+
+    def ensure_space_after_initials(string)
+      string.gsub(/\b([a-z]\.)(?=[a-z0-9]{2,})/i) { "#{Regexp.last_match[1]} " }
+    end
+  end
+end

data/lib/name_tamer/strings.rb

@@ -0,0 +1,9 @@
+# frozen_string_literal: true
+
+require_relative 'strings/core'
+require_relative 'strings/approximations'
+require_relative 'strings/bad_encoding'
+require_relative 'strings/capitalization'
+require_relative 'strings/compound_names'
+require_relative 'strings/name_modifiers'
+require_relative 'strings/spacing'

data/lib/name_tamer/text.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module NameTamer
   class Text
     # All the potential slugs from the string
@@ -8,29 +10,35 @@ module NameTamer
 
     # Split the string into segments (e.g. sentences)
     def segments
-      string.split(%r{(?:[\.\?,:;!]|[[:space:]][/-])[[:space:]]})
+      string.split(%r{(?:[.?,:;!]|[[:space:]][/-])[[:space:]]})
     end
 
     # The string as a slug
     def parameterize
-      @parameterize ||= (
-        string
-        .dup
-        .whitespace_to!(separator)
-        .invalid_chars_to!(separator)
-        .strip_unwanted!(filter)
-        .fix_separators!(separator)
-        .approximate_latin_chars!
-        .presence || '_'
-      ).downcase
+      @parameterize ||= begin
+        slug = Strings.whitespace_to(string, separator)
+        slug = Strings.invalid_chars_to(slug, separator)
+        slug = Strings.strip_unwanted(slug, filter)
+        slug = Strings.fix_separators(slug, separator)
+        slug = Strings.approximate_latin_chars(slug)
+
+        (Strings.presence(slug) || '_').downcase
+      end
     end
 
     def neighbours
-      @neighbours ||= NameTamer[string].array.neighbours.map { |a| a.join('-') }
+      @neighbours ||= contiguous_slices(NameTamer[string].array).map { |words| words.join('-') }
     end
 
     private
 
+    # All the contiguous sub-arrays of an array,
+    # e.g. [1, 2] -> [[1], [1, 2], [2]]
+    def contiguous_slices(array)
+      last_index = array.length - 1
+      0.upto(last_index).flat_map { |i| i.upto(last_index).map { |j| array[i..j] } }
+    end
+
     attr_reader :string, :args
 
     def initialize(string, args = {})
@@ -39,7 +47,7 @@ module NameTamer
     end
 
     def separator
-      @seperator ||= args[:sep] || SLUG_DELIMITER
+      @separator ||= args[:sep] || SLUG_DELIMITER
     end
 
     def rfc3987

data/lib/name_tamer/version.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module NameTamer
-  VERSION = '0.6.0'.freeze
+  VERSION = '1.0.0'
 end

data/lib/name_tamer.rb

@@ -1,8 +1,7 @@
-# encoding: utf-8
+# frozen_string_literal: true
 
 require 'cgi'
-require 'name_tamer/string'
-require 'name_tamer/array'
+require 'name_tamer/strings'
 require 'name_tamer/constants'
 
 module NameTamer

metadata

@@ -1,14 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: name_tamer
 version: !ruby/object:Gem::Version
-  version: 0.6.0
+  version: 1.0.0
 platform: ruby
 authors:
 - Dominic Sayers
-autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-04-19 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies: []
 description: Useful methods for taming names
 email:
@@ -17,40 +16,38 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- ".codeclimate.yml"
-- ".env"
-- ".gitignore"
-- ".hound.yml"
-- ".rspec"
-- ".rubocop.yml"
-- ".travis.yml"
-- Gemfile
-- Guardfile
+- CHANGELOG.md
 - LICENSE
 - README.md
-- Rakefile
-- doc/maintenance.rake
-- doc/prefixes.csv
-- doc/suffixes.csv
 - lib/name-tamer.rb
 - lib/name_tamer.rb
-- lib/name_tamer/array.rb
 - lib/name_tamer/constants.rb
+- lib/name_tamer/constants/adfixes_prefix_person
+- lib/name_tamer/constants/adfixes_suffix_organization
+- lib/name_tamer/constants/adfixes_suffix_person
 - lib/name_tamer/name.rb
-- lib/name_tamer/string.rb
+- lib/name_tamer/name/private_methods_nice_name.rb
+- lib/name_tamer/name/private_methods_simple_name.rb
+- lib/name_tamer/name/utilities.rb
+- lib/name_tamer/strings.rb
+- lib/name_tamer/strings/approximations.rb
+- lib/name_tamer/strings/bad_encoding.rb
+- lib/name_tamer/strings/capitalization.rb
+- lib/name_tamer/strings/compound_names.rb
+- lib/name_tamer/strings/core.rb
+- lib/name_tamer/strings/name_modifiers.rb
+- lib/name_tamer/strings/spacing.rb
 - lib/name_tamer/text.rb
 - lib/name_tamer/version.rb
-- name_tamer.gemspec
-- spec/name_tamer/name_spec.rb
-- spec/name_tamer/string_spec.rb
-- spec/name_tamer/text_spec.rb
-- spec/spec_helper.rb
-- spec/support/names.yml
 homepage: https://github.com/dominicsayers/name_tamer
 licenses:
 - MIT
-metadata: {}
-post_install_message: 
+metadata:
+  homepage_uri: https://github.com/dominicsayers/name_tamer
+  source_code_uri: https://github.com/dominicsayers/name_tamer
+  changelog_uri: https://github.com/dominicsayers/name_tamer/blob/main/CHANGELOG.md
+  bug_tracker_uri: https://github.com/dominicsayers/name_tamer/issues
+  rubygems_mfa_required: 'true'
 rdoc_options: []
 require_paths:
 - lib
@@ -58,22 +55,15 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '0'
+      version: '3.3'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.6.11
-signing_key: 
+rubygems_version: 3.6.9
 specification_version: 4
 summary: 'Example: NameTamer[''Mr. John Q. Smith III, MD''].simple_name # => John
   Smith'
-test_files:
-- spec/name_tamer/name_spec.rb
-- spec/name_tamer/string_spec.rb
-- spec/name_tamer/text_spec.rb
-- spec/spec_helper.rb
-- spec/support/names.yml
+test_files: []

data/.codeclimate.yml

@@ -1,18 +0,0 @@
----
-engines:
-  duplication:
-    enabled: true
-    config:
-      languages:
-      - ruby
-  fixme:
-    enabled: true
-  rubocop:
-    enabled: true
-ratings:
-  paths:
-  - "**.rb"
-exclude_paths:
-- script/
-- spec/
-- doc/

data/.env

@@ -1 +0,0 @@
-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

@@ -1,26 +0,0 @@
-*.gem
-
-*.rbc
-capybara-*.html
-/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
-
-.ruby-version
-.ruby-gemset
-Gemfile.lock
-
-# unless supporting rvm < 1.11.0 or doing something fancy, ignore this:
-.rvmrc

data/.hound.yml

@@ -1,6 +0,0 @@
----
-ruby:
-  enabled: true
-  config_file: .rubocop.yml
-coffee_script:
-  enabled: true

data/.rspec

@@ -1,2 +0,0 @@
---color
---require spec_helper

data/.rubocop.yml

@@ -1,63 +0,0 @@
----
-AllCops:
-  TargetRubyVersion: 2.0
-  DisplayCopNames: true
-  Exclude:
-    - 'tmp/**/*'
-    - '**/*.rake'
-
-Metrics/BlockLength:
-  CountComments: false  # count full line comments?
-  Exclude:
-    - '**/*_spec.rb'
-
-LineLength:
-  Description: 'Limit lines to 120 characters.'
-  Max: 120
-  Enabled: true
-
-MethodLength:
-  Description: 'Avoid methods longer than 10 lines of code.'
-  Max: 23
-  Enabled: true
-
-Documentation:
-  Description: 'Document classes and non-namespace modules.'
-  Enabled: false
-
-FileName:
-  Description: 'Use snake_case for source file names.'
-  Enabled: false
-
-DotPosition:
-  Description: 'Checks the position of the dot in multi-line method calls.'
-  EnforcedStyle: leading
-  # EnforcedStyle: trailing
-  Enabled: true
-
-StringLiterals:
-  EnforcedStyle: single_quotes
-  Enabled: true
-
-CyclomaticComplexity:
-  Description: 'Avoid complex methods.'
-  Max: 8
-
-ClassLength:
-  Description: 'Avoid classes longer than 100 lines of code.'
-  CountComments: false  # count full line comments?
-  Max: 334
-
-ExtraSpacing:
-  Enabled: true
-
-Style/PercentLiteralDelimiters:
-  # Hound and CodeClimate are currently using an old version of Rubocop with
-  # different defaults, so we set them explicitly here.
-  PreferredDelimiters:
-    default: ()
-    '%i': '[]'
-    '%I': '[]'
-    '%r': '{}'
-    '%w': '[]'
-    '%W': '[]'

data/.travis.yml

@@ -1,13 +0,0 @@
----
-language: ruby
-dist: trusty
-rvm:
-  - 2.4.0
-  - 2.3
-  - 2.2
-  - 2.1
-  - 2.0
-before_install:
-  - gem update bundler
-script: bundle exec rspec
-after_success: bundle exec codeclimate-test-reporter

data/Gemfile

@@ -1,20 +0,0 @@
-source 'https://rubygems.org'
-gemspec
-ruby RUBY_VERSION
-
-group :development do
-  gem 'bundler'
-  gem 'gem-release'
-  gem 'guard'
-  gem 'guard-rspec'
-  gem 'guard-rubocop'
-end
-
-group :test do
-  gem 'codeclimate-test-reporter'
-  gem 'coveralls'
-  gem 'fuubar'
-  gem 'rspec'
-  gem 'rspec_junit_formatter'
-  gem 'simplecov', '~> 0.13'
-end

data/Guardfile

@@ -1,16 +0,0 @@
-guard :rubocop do
-  watch(/.+\.rb$/)
-  watch(%r{(?:.+/)?\.rubocop\.yml$}) { |m| File.dirname(m[0]) }
-end
-
-guard(
-  :rspec,
-  all_after_pass: true,
-  all_on_start: true,
-  cmd: 'bundle exec rspec --fail-fast --format documentation'
-) do
-  watch(%r{^spec/.+_spec\.rb$})
-  watch(%r{^lib/(.+)\.rb$}) { |m| "spec/#{m[1]}_spec.rb" }
-  watch('spec/spec_helper.rb') { 'spec' }
-  watch(%r{^spec/support/.+\.rb$}) { 'spec' }
-end

data/Rakefile

@@ -1,14 +0,0 @@
-#!/usr/bin/env rake
-require 'bundler/gem_tasks'
-
-begin
-  require 'rspec/core/rake_task'
-
-  RSpec::Core::RakeTask.new(:spec)
-
-  task default: :spec
-rescue LoadError
-  puts 'rspec is not available'
-end
-
-Dir.glob('doc/*.rake').each { |r| load r }