name_tamer 0.6.1 → 1.0.2

data/lib/name_tamer/strings/bad_encoding.rb

@@ -0,0 +1,148 @@
+# frozen_string_literal: true
+
+# When strings are mistakenly encoded as single-byte character sets, instead
+# of UTF-8, there are some distinctive character combinations that we can spot
+# and fix
+# Useful table here http://www.i18nqa.com/debug/utf8-debug.html
+module NameTamer
+  module Strings
+    extend self
+
+    # Strings that were wrongly encoded with single-byte encodings sometimes
+    # have tell-tale substrings that we can put back into the correct UTF-8
+    # character
+    def fix_encoding_errors(string)
+      string.gsub(BAD_ENCODING_PATTERNS) { |substring| BAD_ENCODING[substring] || substring }
+    end
+
+    BAD_ENCODING = {
+      "\xC3\x8D" => 'Í',
+      "\xC3\x8F" => 'Ï',
+      "\xC3\x90" => 'Ð',
+      "\xC3\x9D" => 'Ý',
+      ' ' => ' ',
+      '¡' => '¡',
+      '¢' => '¢',
+      '£' => '£',
+      '¤' => '¤',
+      'Â¥' => '¥',
+      '¦' => '¦',
+      '§' => '§',
+      '¨' => '¨',
+      '©' => '©',
+      'ª' => 'ª',
+      '«' => '«',
+      '¬' => '¬',
+      '­' => '­',
+      '®' => '®',
+      '¯' => '¯',
+      '°' => '°',
+      '±' => '±',
+      '²' => '²',
+      '³' => '³',
+      '´' => '´',
+      'µ' => 'µ',
+      '¶' => '¶',
+      '·' => '·',
+      '¸' => '¸',
+      '¹' => '¹',
+      'º' => 'º',
+      '»' => '»',
+      '¼' => '¼',
+      '½' => '½',
+      '¾' => '¾',
+      '¿' => '¿',
+      '€' => '€',
+      'â„¢' => '™',
+      '”' => '”', # Note the invisible Ux009D in the key
+      '†' => '†',
+      '‡' => '‡',
+      '•' => '•',
+      '…' => '…',
+      '‰' => '‰',
+      '′' => '′', # Manually added. Some seem to use this instead of Ux2019
+      '‹' => '‹',
+      '›' => '›',
+      '“' => '“',
+      '‚' => '‚',
+      '„' => '„',
+      '‘' => '‘',
+      '–' => '–',
+      '—' => '—',
+      '’' => '’',
+      'à' => 'à',
+      'á' => 'á',
+      'â' => 'â',
+      'ã' => 'ã',
+      'ä' => 'ä',
+      'Ã¥' => 'å',
+      'æ' => 'æ',
+      'ç' => 'ç',
+      'è' => 'è',
+      'é' => 'é',
+      'ê' => 'ê',
+      'ë' => 'ë',
+      'ì' => 'ì',
+      'í' => 'í',
+      'î' => 'î',
+      'ï' => 'ï',
+      'ð' => 'ð',
+      'ñ' => 'ñ',
+      'ò' => 'ò',
+      'ó' => 'ó',
+      'ô' => 'ô',
+      'õ' => 'õ',
+      'ö' => 'ö',
+      '÷' => '÷',
+      'ø' => 'ø',
+      'ù' => 'ù',
+      'ú' => 'ú',
+      'û' => 'û',
+      'ü' => 'ü',
+      'ý' => 'ý',
+      'þ' => 'þ',
+      'ÿ' => 'ÿ',
+      'ß' => 'ß',
+      'ÃŒ' => 'Ì',
+      'Ãœ' => 'Ü',
+      'Ê' => 'Ê',
+      'Ú' => 'Ú',
+      'ÃŽ' => 'Î',
+      'Þ' => 'Þ',
+      'Ã' => 'Ã',
+      'È' => 'È',
+      'Ø' => 'Ø',
+      'Ö' => 'Ö',
+      '×' => '×',
+      'Ñ' => 'Ñ',
+      'Ã’' => 'Ò',
+      'Â' => 'Â',
+      'Ó' => 'Ó',
+      'Ô' => 'Ô',
+      'Ä' => 'Ä',
+      'Æ' => 'Æ',
+      'Ç' => 'Ç',
+      'Õ' => 'Õ',
+      'Ã…' => 'Å',
+      'É' => 'É',
+      'Ë' => 'Ë',
+      'Û' => 'Û',
+      'À' => 'À',
+      'Ù' => 'Ù',
+      "Ã\uFFFD" => 'Á', # second byte of mangled Á decodes to U+FFFD REPLACEMENT CHARACTER
+      'Å ' => 'Š',
+      'Å¡' => 'š',
+      'Ÿ' => 'Ÿ',
+      'Ž' => 'Ž',
+      'ž' => 'ž',
+      'Å’' => 'Œ',
+      'Å“' => 'œ',
+      'Æ’' => 'ƒ',
+      'Ëœ' => '˜',
+      'ˆ' => 'ˆ',
+      "\x00" => '', # Manually added to avoid Bad Argument exception
+    }.freeze
+
+    BAD_ENCODING_PATTERNS = /(#{BAD_ENCODING.keys.join('|')})/
+  end
+end

data/lib/name_tamer/strings/capitalization.rb

@@ -0,0 +1,46 @@
+# frozen_string_literal: true
+
+module NameTamer
+  module Strings
+    extend self
+
+    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
+    extend self
+
+    # 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
+    extend self
+
+    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
+    extend self
+
+    # 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
+    extend self
+
+    # 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

@@ -10,29 +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 = {})

data/lib/name_tamer/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module NameTamer
-  VERSION = '0.6.1'
+  VERSION = '1.0.2'
 end

data/lib/name_tamer.rb

@@ -1,8 +1,7 @@
 # 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: 0.6.1
+  version: 1.0.2
 platform: ruby
 authors:
 - Dominic Sayers
-autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-08-19 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies: []
 description: Useful methods for taming names
 email:
@@ -17,35 +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
 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
@@ -53,16 +55,14 @@ 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: 2.7.7
-signing_key: 
+rubygems_version: 4.0.16
 specification_version: 4
 summary: 'Example: NameTamer[''Mr. John Q. Smith III, MD''].simple_name # => John
   Smith'

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

@@ -1,27 +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
-.byebug_history
-
-# 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

@@ -1,61 +0,0 @@
----
-AllCops:
-  DisplayCopNames: true
-  DisplayStyleGuide: true
-  Exclude:
-    - bin/**/*
-    - tmp/**/*
-    - '**/*.rake'
-
-Layout/DotPosition:
-  EnforcedStyle: leading
-  Enabled: true
-
-Layout/ExtraSpacing:
-  Enabled: true
-
-Metrics/BlockLength:
-  CountComments: false  # count full line comments?
-  Exclude:
-    - '**/*_spec.rb'
-
-Metrics/ClassLength:
-  CountComments: false  # count full line comments?
-  Exclude:
-    - lib/name_tamer/name.rb
-    - lib/name_tamer/string.rb
-
-Metrics/CyclomaticComplexity:
-  Max: 8
-
-Metrics/LineLength:
-  Max: 120
-  Enabled: true
-
-Metrics/MethodLength:
-  Max: 23
-  Enabled: true
-
-Metrics/ModuleLength:
-  CountComments: false  # count full line comments?
-  Exclude:
-    - lib/name_tamer/constants.rb
-
-Naming/FileName:
-  Enabled: false
-
-Style/Documentation:
-  Enabled: false
-
-Style/MutableConstant:
-  Enabled: true
-
-Style/StringLiterals:
-  EnforcedStyle: single_quotes
-  Enabled: true
-
-Style/TrailingCommaInArrayLiteral:
-  EnforcedStyleForMultiline: comma
-
-Style/TrailingCommaInHashLiteral:
-  EnforcedStyleForMultiline: comma

data/.travis.yml

@@ -1,11 +0,0 @@
----
-language: ruby
-dist: trusty
-rvm:
-  - 2.5
-  - 2.4
-  - 2.3
-before_install:
-  - gem update bundler
-script: bundle exec rspec
-after_success: bundle exec codeclimate-test-reporter