name_tamer 0.6.0

data/lib/name_tamer/string.rb

@@ -0,0 +1,280 @@
+# encoding: utf-8
+
+class String
+  unless respond_to? :presence
+    def presence
+      self unless empty?
+    end
+  end
+
+  # Strip illegal characters out completely
+  def strip_unwanted!(filter)
+    substitute!(filter, '')
+  end
+
+  def strip_or_self!
+    strip! || self
+  end
+
+  # Change any whitespace into our separator character
+  def whitespace_to!(separator)
+    substitute!(/[[:space:]]+/, separator)
+  end
+
+  # Ensure commas have exactly one space after them
+  def space_around_comma!
+    substitute!(/[[:space:]]*,[[:space:]]*/, ', ')
+  end
+
+  # Change some characters embedded in words to our separator character
+  # e.g. example.com -> example-com
+  def invalid_chars_to!(separator)
+    substitute!(%r{(?<![[:space:]])[\.\/](?![[:space:]])}, separator)
+  end
+
+  # Unescape percent-encoded characters
+  # This might introduce UTF-8 invalid byte sequence
+  # so we take precautions
+  def safe_unescape!
+    string = URI.unescape(self)
+  rescue Encoding::CompatibilityError # e.g. "\u2019%80"
+    return self
+  else
+    return self if self == string
+    replace string
+    ensure_safe!
+  end
+
+  # Remove HTML entities
+  def unescape_html!
+    replace CGI.unescapeHTML self
+  end
+
+  # Make sure separators are not where they shouldn't be
+  def fix_separators!(separator)
+    return self if separator.nil? || separator.empty?
+
+    r = Regexp.escape(separator)
+
+    # No more than one of the separator in a row.
+    substitute!(/#{r}{2,}/, separator)
+
+    # Remove leading/trailing separator.
+    substitute!(/^#{r}|#{r}$/i, '')
+  end
+
+  # Any characters that resemble latin characters might usefully be
+  # transliterated into ones that are easy to type on an anglophone
+  # keyboard.
+  def approximate_latin_chars!
+    gsub!(/[^\x00-\x7f]/u) { |char| APPROXIMATIONS[char] || char } || self
+  end
+
+  # 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!
+    gsub!(BAD_ENCODING_PATTERNS) { |substring| BAD_ENCODING[substring] || substring } || self
+  end
+
+  def upcase_first_letter!
+    gsub!(/\b\w/, &:upcase) || self
+  end
+
+  def downcase_after_apostrophe!
+    gsub!(/\'\w\b/, &:downcase) || self # 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!
+    if self =~ /\bMac[A-Za-z]{2,}[^acizj]\b/ || self =~ /\bMc/
+      gsub!(/\b(Ma?c)([A-Za-z]+)/) { |_| Regexp.last_match[1] + Regexp.last_match[2].capitalize }
+
+      # Fix Mac exceptions
+      %w[
+        MacEdo MacEvicius MacHado MacHar MacHin MacHlin MacIas MacIulis MacKie
+        MacKle MacKlin MacKmin MacKmurdo MacQuarie MacLise MacKenzie
+      ].each { |mac_name| substitute!(/\b#{mac_name}/, mac_name.capitalize) }
+    end
+
+    self # Allows chaining
+  end
+
+  # Fix ff wierdybonks
+  def fix_ff!
+    %w[
+      Fforbes Fforde Ffinch Ffrench Ffoulkes
+    ].each { |ff_name| substitute!(ff_name, ff_name.downcase) }
+
+    self # Allows chaining
+  end
+
+  # 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!
+    NAME_MODIFIERS.each do |modifier|
+      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!
+    self # Allows chaining
+  end
+
+  def fix_apostrophe_modifiers!
+    %w[Dell D].each do |modifier|
+      gsub!(/(.#{modifier}')(\w)/) { |_| "#{Regexp.last_match[1].rstrip.downcase}#{Regexp.last_match[2]}" }
+    end
+
+    self # Allows chaining
+  end
+
+  # Upcase words with no vowels, e.g JPR Williams
+  # Except Ng
+  def upcase_initials!
+    gsub!(/\b([bcdfghjklmnpqrstvwxz]+)\b/i) { |_| Regexp.last_match[1].upcase }
+    gsub!(/\b(NG)\b/i) { |_| Regexp.last_match[1].capitalize } || self # http://en.wikipedia.org/wiki/Ng
+  end
+
+  # Fix known last names that have spaces (not hyphens!)
+  def nbsp_in_compound_name!
+    COMPOUND_NAMES.each do |compound_name|
+      substitute!(compound_name, compound_name.tr(ASCII_SPACE, NONBREAKING_SPACE))
+    end
+
+    self # Allows chaining
+  end
+
+  def nbsp_in_name_modifier!
+    NAME_MODIFIERS.each do |modifier|
+      gsub!(/([[:space:]]#{modifier})([[:space:]])/i) { |_| "#{Regexp.last_match[1]}#{NONBREAKING_SPACE}" }
+    end
+
+    self # Allows chaining
+  end
+
+  def remove_periods_from_initials!
+    gsub!(/\b([a-z])\./i) { |_| Regexp.last_match[1] } || self
+  end
+
+  def remove_spaces_from_initials!
+    gsub!(/\b([a-z])(\.)* \b(?![a-z0-9'\u00C0-\u00FF]{2,})/i) do |_|
+      "#{Regexp.last_match[1]}#{Regexp.last_match[2]}"
+    end || self
+  end
+
+  def ensure_space_after_initials!
+    gsub!(/\b([a-z]\.)(?=[a-z0-9]{2,})/i) { |_| "#{Regexp.last_match[1]} " } || self
+  end
+
+  def ensure_safe!
+    encode!('UTF-8', invalid: :replace, undef: :replace, replace: '') # Doesn't fully work in Ruby 2.0
+  end
+
+  def substitute!(pattern, replacement)
+    gsub!(pattern, replacement) || self
+  end
+
+  NONBREAKING_SPACE = "\u00a0".freeze
+  ASCII_SPACE = ' '.freeze
+
+  COMPOUND_NAMES = [
+    'Lane Fox', 'Bonham Carter', 'Pitt Rivers', 'Lloyd Webber', 'Sebag Montefiore', 'Holmes à Court', 'Holmes a Court',
+    'Baron Cohen', 'Strang Steel', 'Wingfield Digby',
+    'Service Company', 'Corporation Company', 'Corporation System', 'Incorporations Limited'
+  ].freeze
+
+  NAME_MODIFIERS = [
+    'Al', 'Ap', 'Ben', 'Dell[ae]', 'D[aeiou]', 'De[lrn]', 'D[ao]s', 'El', 'La', 'L[eo]', 'V[ao]n', 'Of', 'San',
+    'St[\.]?', 'Zur'
+  ].freeze
+
+  # Transliterations (like the i18n defaults)
+  # see https://github.com/svenfuchs/i18n/blob/master/lib/i18n/backend/transliterator.rb
+  APPROXIMATIONS = {
+    'À' => 'A', 'Á' => 'A', 'Â' => 'A', 'Ã' => 'A', 'Ä' => 'A', 'Å' => 'A', 'Æ' => 'AE',
+    'Ç' => 'C', 'È' => 'E', 'É' => 'E', 'Ê' => 'E', 'Ë' => 'E', 'Ì' => 'I', 'Í' => 'I',
+    'Î' => 'I', 'Ï' => 'I', 'Ð' => 'D', 'Ñ' => 'N', 'Ò' => 'O', 'Ó' => 'O', 'Ô' => 'O',
+    'Õ' => 'O', 'Ö' => 'O', '×' => 'x', 'Ø' => 'O', 'Ù' => 'U', 'Ú' => 'U', 'Û' => 'U',
+    'Ü' => 'U', 'Ý' => 'Y', 'Þ' => 'Th', 'ß' => 'ss', 'à' => 'a', 'á' => 'a', 'â' => 'a',
+    'ã' => 'a', 'ä' => 'a', 'å' => 'a', 'æ' => 'ae', 'ç' => 'c', 'è' => 'e', 'é' => 'e',
+    'ê' => 'e', 'ë' => 'e', 'ì' => 'i', 'í' => 'i', 'î' => 'i', 'ï' => 'i', 'ð' => 'd',
+    'ñ' => 'n', 'ò' => 'o', 'ó' => 'o', 'ô' => 'o', 'õ' => 'o', 'ö' => 'o', 'ø' => 'o',
+    'ù' => 'u', 'ú' => 'u', 'û' => 'u', 'ü' => 'u', 'ý' => 'y', 'þ' => 'th', 'ÿ' => 'y',
+    'Ā' => 'A', 'ā' => 'a', 'Ă' => 'A', 'ă' => 'a', 'Ą' => 'A', 'ą' => 'a', 'Ć' => 'C',
+    'ć' => 'c', 'Ĉ' => 'C', 'ĉ' => 'c', 'Ċ' => 'C', 'ċ' => 'c', 'Č' => 'C', 'č' => 'c',
+    'Ď' => 'D', 'ď' => 'd', 'Đ' => 'D', 'đ' => 'd', 'Ē' => 'E', 'ē' => 'e', 'Ĕ' => 'E',
+    'ĕ' => 'e', 'Ė' => 'E', 'ė' => 'e', 'Ę' => 'E', 'ę' => 'e', 'Ě' => 'E', 'ě' => 'e',
+    'Ĝ' => 'G', 'ĝ' => 'g', 'Ğ' => 'G', 'ğ' => 'g', 'Ġ' => 'G', 'ġ' => 'g', 'Ģ' => 'G',
+    'ģ' => 'g', 'Ĥ' => 'H', 'ĥ' => 'h', 'Ħ' => 'H', 'ħ' => 'h', 'Ĩ' => 'I', 'ĩ' => 'i',
+    'Ī' => 'I', 'ī' => 'i', 'Ĭ' => 'I', 'ĭ' => 'i', 'Į' => 'I', 'į' => 'i', 'İ' => 'I',
+    'ı' => 'i', 'IJ' => 'IJ', 'ij' => 'ij', 'Ĵ' => 'J', 'ĵ' => 'j', 'Ķ' => 'K', 'ķ' => 'k',
+    'ĸ' => 'k', 'Ĺ' => 'L', 'ĺ' => 'l', 'Ļ' => 'L', 'ļ' => 'l', 'Ľ' => 'L', 'ľ' => 'l',
+    'Ŀ' => 'L', 'ŀ' => 'l', 'Ł' => 'L', 'ł' => 'l', 'Ń' => 'N', 'ń' => 'n', 'Ņ' => 'N',
+    'ņ' => 'n', 'Ň' => 'N', 'ň' => 'n', 'ʼn' => "'n", 'Ŋ' => 'NG', 'ŋ' => 'ng',
+    'Ō' => 'O', 'ō' => 'o', 'Ŏ' => 'O', 'ŏ' => 'o', 'Ő' => 'O', 'ő' => 'o', 'Œ' => 'OE',
+    'œ' => 'oe', 'Ŕ' => 'R', 'ŕ' => 'r', 'Ŗ' => 'R', 'ŗ' => 'r', 'Ř' => 'R', 'ř' => 'r',
+    'Ś' => 'S', 'ś' => 's', 'Ŝ' => 'S', 'ŝ' => 's', 'Ş' => 'S', 'ş' => 's', 'Š' => 'S',
+    'š' => 's', 'Ţ' => 'T', 'ţ' => 't', 'Ť' => 'T', 'ť' => 't', 'Ŧ' => 'T', 'ŧ' => 't',
+    'Ũ' => 'U', 'ũ' => 'u', 'Ū' => 'U', 'ū' => 'u', 'Ŭ' => 'U', 'ŭ' => 'u', 'Ů' => 'U',
+    'ů' => 'u', 'Ű' => 'U', 'ű' => 'u', 'Ų' => 'U', 'ų' => 'u', 'Ŵ' => 'W', 'ŵ' => 'w',
+    'Ŷ' => 'Y', 'ŷ' => 'y', 'Ÿ' => 'Y', 'Ź' => 'Z', 'ź' => 'z', 'Ż' => 'Z', 'ż' => 'z',
+    'Ž' => 'Z', 'ž' => 'z'
+  }.freeze
+
+  # 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
+  BAD_ENCODING = {
+    '€' => '€', '‚' => '‚', 'Æ’' => 'ƒ', '„' => '„', '…' => '…',
+    '†' => '†', '‡' => '‡', 'ˆ' => 'ˆ', '‰' => '‰', 'Å ' => 'Š',
+    '‹' => '‹', 'Å’' => 'Œ', 'Ž' => 'Ž', '‘' => '‘', '’' => '’',
+    '“' => '“',
+    '”' => '”', # Note the invisible Ux009D in the key
+    '′' => '′', # Manually added. Some seem to use this instead of Ux2019
+    '•' => '•', '–' => '–', '—' => '—',
+    'Ëœ' => '˜', 'â„¢' => '™', 'Å¡' => 'š', '›' => '›', 'Å“' => 'œ',
+    'ž' => 'ž', 'Ÿ' => 'Ÿ', ' ' => ' ', '¡' => '¡', '¢' => '¢',
+    '£' => '£', '¤' => '¤', 'Â¥' => '¥', '¦' => '¦', '§' => '§',
+    '¨' => '¨', '©' => '©', 'ª' => 'ª', '«' => '«', '¬' => '¬',
+    '­' => '­', '®' => '®', '¯' => '¯', '°' => '°', '±' => '±',
+    '²' => '²', '³' => '³', '´' => '´', 'µ' => 'µ', '¶' => '¶',
+    '·' => '·', '¸' => '¸', '¹' => '¹', 'º' => 'º', '»' => '»',
+    '¼' => '¼', '½' => '½', '¾' => '¾', '¿' => '¿', 'À' => 'À',
+    'Ã�' => 'Á', 'Â' => 'Â', 'Ã' => 'Ã', 'Ä' => 'Ä', 'Ã…' => 'Å',
+    'Æ' => 'Æ', 'Ç' => 'Ç', 'È' => 'È', 'É' => 'É', 'Ê' => 'Ê',
+    'Ë' => 'Ë', 'ÃŒ' => 'Ì', "\xC3\x8D" => 'Í', 'ÃŽ' => 'Î', "\xC3\x8F" => 'Ï',
+    "\xC3\x90" => 'Ð', 'Ñ' => 'Ñ', 'Ã’' => 'Ò', 'Ó' => 'Ó', 'Ô' => 'Ô',
+    'Õ' => 'Õ', 'Ö' => 'Ö', '×' => '×', 'Ø' => 'Ø', 'Ù' => 'Ù',
+    'Ú' => 'Ú', 'Û' => 'Û', 'Ãœ' => 'Ü', "\xC3\x9D" => 'Ý', 'Þ' => 'Þ',
+    'ß' => 'ß', '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',
+    "\x00" => '' # Manually added to avoid Bad Argument exception
+  }.freeze
+
+  BAD_ENCODING_PATTERNS = /(#{BAD_ENCODING.keys.join('|')})/
+
+  # Colorize strings
+  colors = %w[black red green yellow blue magenta cyan white]
+
+  colors.each_with_index do |fg_color, i|
+    fg = 30 + i
+    define_method(fg_color) { ansi_attributes(fg) }
+
+    colors.each_with_index do |bg_color, j|
+      define_method("#{fg_color}_on_#{bg_color}") { ansi_attributes(fg, 40 + j) }
+    end
+  end
+
+  def ansi_attributes(*args)
+    "\e[#{args.join(';')}m#{self}\e[0m"
+  end
+end

data/lib/name_tamer/text.rb

@@ -0,0 +1,53 @@
+module NameTamer
+  class Text
+    # All the potential slugs from the string
+    # e.g. 'lorem ipsum dolor' -> ['lorem', 'ipsum' ,'dolor', 'lorem-ipsum', 'ipsum-dolor', 'lorem-ipsum-dolor']
+    def slugs
+      @slugs ||= segments.flat_map { |s| self.class.new(s).neighbours }.uniq
+    end
+
+    # Split the string into segments (e.g. sentences)
+    def segments
+      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
+    end
+
+    def neighbours
+      @neighbours ||= NameTamer[string].array.neighbours.map { |a| a.join('-') }
+    end
+
+    private
+
+    attr_reader :string, :args
+
+    def initialize(string, args = {})
+      @string = string
+      @args = args
+    end
+
+    def separator
+      @seperator ||= args[:sep] || SLUG_DELIMITER
+    end
+
+    def rfc3987
+      @rfc3987 ||= args[:rfc3987] || false
+    end
+
+    def filter
+      @filter ||= args[:filter] || (rfc3987 ? FILTER_RFC3987 : FILTER_COMPAT)
+    end
+  end
+end

data/lib/name_tamer/version.rb

@@ -0,0 +1,3 @@
+module NameTamer
+  VERSION = '0.6.0'.freeze
+end

data/name_tamer.gemspec

@@ -0,0 +1,19 @@
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'name_tamer/version'
+
+Gem::Specification.new do |spec|
+  spec.name = 'name_tamer'
+  spec.version = NameTamer::VERSION
+  spec.authors = ['Dominic Sayers']
+  spec.email = ['dominic@sayers.cc']
+  spec.description = 'Useful methods for taming names'
+  spec.summary = "Example: NameTamer['Mr. John Q. Smith III, MD'].simple_name # => John Smith"
+  spec.homepage = 'https://github.com/dominicsayers/name_tamer'
+  spec.license = 'MIT'
+
+  spec.files = `git ls-files`.split($INPUT_RECORD_SEPARATOR)
+  spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files = spec.files.grep(%r{^(test|spec|features|coverage)/})
+  spec.require_paths = ['lib']
+end

data/spec/name_tamer/name_spec.rb

@@ -0,0 +1,95 @@
+# encoding: utf-8
+
+describe NameTamer::Name do
+  context 'invalid byte sequence in UTF-8' do
+    let(:name_data) { { n: "\xc3\x28", t: :person, nn: '()', sn: '()', s: '_' } } # Invalid byte sequence in UTF-8
+
+    if Gem::Version.new(RUBY_VERSION) <= Gem::Version.new('2')
+      it 'fails to correct invalid byte sequence' do
+        name = name_data[:n]
+        expect { NameTamer[name, contact_type: name_data[:t]].slug }.to raise_error(
+          ArgumentError,
+          'invalid byte sequence in UTF-8'
+        )
+      end
+    else
+      it 'makes a slug' do
+        name = name_data[:n]
+        expect(NameTamer[name, contact_type: name_data[:t]].slug).to eq(name_data[:s])
+      end
+
+      it 'makes a nice name' do
+        name = name_data[:n]
+        nice_name = NameTamer[name, contact_type: name_data[:t]].nice_name
+        expect(nice_name).to eq(name_data[:nn])
+      end
+
+      it 'makes a searchable name' do
+        name = name_data[:n]
+        expect(NameTamer[name, contact_type: name_data[:t]].simple_name).to eq(name_data[:sn])
+      end
+    end
+  end
+
+  context 'all ruby versions' do
+    let(:names) { YAML.load_file(File.join('spec', 'support', 'names.yml')) }
+
+    it 'loads the examples correctly' do
+      expect(names.length).to eq(152) # Number of examples
+    end
+
+    it 'makes a slug' do
+      names.each do |name_data|
+        name = name_data[:n]
+        expect(NameTamer[name, contact_type: name_data[:t]].slug).to eq(name_data[:s].downcase)
+      end
+    end
+
+    it 'makes a nice name' do
+      names.each do |name_data|
+        name = name_data[:n]
+        nice_name = NameTamer[name, contact_type: name_data[:t]].nice_name
+        expect(nice_name).to eq(name_data[:nn])
+      end
+    end
+
+    it 'makes a searchable name' do
+      names.each do |name_data|
+        name = name_data[:n]
+        expect(NameTamer[name, contact_type: name_data[:t]].simple_name).to eq(name_data[:sn])
+      end
+    end
+  end
+end
+
+describe 'contact type inference' do
+  it 'infers that "Mr. John Smith" is a person' do
+    expect(NameTamer['Mr. John Smith'].contact_type).to eq(:person)
+  end
+
+  it 'infers that "Di Doo Doo d.o.o." is an organization' do
+    expect(NameTamer['Di Doo Doo d.o.o.'].contact_type).to eq(:organization)
+  end
+
+  it 'infers that "DiDooDoo" is an organization' do
+    expect(NameTamer['DiDooDoo'].contact_type).to eq(:organization)
+  end
+
+  it 'infers that "John Smith" is a person' do
+    expect(NameTamer['John Smith'].contact_type).to eq(:person)
+  end
+
+  it 'announces a change in contact type' do
+    nt = NameTamer::Name.new 'John Smith', contact_type: :person
+    nt.contact_type = :organization
+    expect(nt.contact_type).to eq(:organization)
+  end
+end
+
+describe 'iteration' do
+  it 'iterates through the significant words of a name' do
+    words = []
+    NameTamer['John Smith'].each_word { |w| words << w }
+    expect(words).to include('john', 'smith')
+  end
+end