name_tamer 0.6.1 → 1.0.2

data/lib/name_tamer/constants.rb

@@ -3,7 +3,7 @@
 module NameTamer
   NONBREAKING_SPACE = "\u00a0"
   ASCII_SPACE = ' '
-  ADFIX_JOINERS = "[#{ASCII_SPACE}-]"
+  ADFIX_JOINERS = "[#{ASCII_SPACE}-]".freeze
   SLUG_DELIMITER = '-'
   ZERO_WIDTH_FILTER = /[\u180E\u200B\u200C\u200D\u2063\uFEFF]/
 
@@ -39,9 +39,9 @@ module NameTamer
   ALPHA = 'A-Za-z'
   DIGIT = '0-9'
   UCSCHAR = '\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF'
-  IUNRESERVED = "#{ALPHA}#{DIGIT}\\-\\._~#{UCSCHAR}"
+  IUNRESERVED = "#{ALPHA}#{DIGIT}\\-\\._~#{UCSCHAR}".freeze
   SUBDELIMS = '!$&\'\(\)\*+,;='
-  ISEGMENT_NZ_NC = "#{IUNRESERVED}#{SUBDELIMS}@" # pct-encoded not needed
+  ISEGMENT_NZ_NC = "#{IUNRESERVED}#{SUBDELIMS}@".freeze # pct-encoded not needed
   FILTER_RFC3987 = /[^#{ISEGMENT_NZ_NC}]/
   FILTER_COMPAT = /[^#{ALPHA}#{DIGIT}\-_#{UCSCHAR}]/
 
@@ -49,54 +49,14 @@ module NameTamer
   # If you add to the list, you can use spaces and dots where appropriate
   # Ensure any single letters are followed by a dot because we'll add one to the string
   # during processing, e.g. "y Cia." should be "y. Cia."
+
+  private_class_method def self.get_constants_from(filename)
+    File.readlines(Pathname.new(__dir__).join('constants', filename), chomp: true).reject(&:empty?)
+  end
+
   ADFIXES = {
     prefix: {
-      person: [
-        'Baroness',
-        'Capt.',
-        'Captain',
-        'Col.',
-        'Colonel',
-        'Dame',
-        'Doctor',
-        'Doktor',
-        'Dr.',
-        'Frau',
-        'Herr',
-        'Judge',
-        'Justice',
-        'Lady',
-        'Lieut.',
-        'Lieutenant',
-        'Lord',
-        'Madame',
-        'Major',
-        'Master',
-        'Matron',
-        'Messrs.',
-        'Mgr.',
-        'Miss',
-        'Mister',
-        'Mlle.',
-        'Mme.',
-        'Mons.',
-        'Mr. & Mrs.',
-        'Mr. and Mrs.',
-        'Mr.',
-        'Mrs.',
-        'Ms.',
-        'Msgr.',
-        'Prof.',
-        'Professor',
-        'Rev.',
-        'Reverend',
-        'Sir',
-        'Sister',
-        'The Hon.',
-        'The Lady.',
-        'The Lord',
-        'The Rt. Hon.',
-      ],
+      person: get_constants_from('adfixes_prefix_person'),
       organization: [
         'Fa.',
         'P.T. Tbk.',
@@ -106,369 +66,24 @@ module NameTamer
       before: '\\A', after: ADFIX_JOINERS
     },
     suffix: {
-      person: [
-        'A.A.M.S.',
-        'A.C.A.',
-        'A.C.C.',
-        'A.C.C.A.',
-        'A.C.M.A.',
-        'A.E.P.',
-        'A.I.F.',
-        'A.I.F.A.',
-        'A.S.A.',
-        'A.W.M.A.',
-        'B.A.',
-        'B.Ed.',
-        'B.Eng.',
-        'B.Sc.',
-        'B.Tech.',
-        'C.A.',
-        'C.A.I.A.',
-        'C.A.P.M.',
-        'C.B.V.',
-        'C.C.I.M.',
-        'C.D.F.A.',
-        'C.E.M.',
-        'C.E.P.P.',
-        'C.Eng.',
-        'C.F.A.',
-        'C.F.B.S.',
-        'C.F.F.',
-        'C.F.P.',
-        'C.F.S.',
-        'C.G.A.',
-        'C.G.B.',
-        'C.G.M.A.',
-        'C.G.P.',
-        'C.I.M.',
-        'C.I.S.S.P.',
-        'C.I.T.P.',
-        'C.L.P.',
-        'C.L.T.C.',
-        'C.L.U.',
-        'C.M.A.',
-        'C.M.T.',
-        'C.P.A.',
-        'C.P.C.C.',
-        'C.R.P.C.',
-        'C.R.P.S.',
-        'C.S.O.X.',
-        'C.S.S.D.',
-        'C.T.A.',
-        'C.W.S.',
-        'Cantab.',
-        'Ch.F.C.',
-        'Chartered F.C.S.I.',
-        'Chartered M.C.S.I.',
-        'D.B.E.',
-        'D.D.S.',
-        'D.Phil.',
-        'D.V.M.',
-        'Dip. D.M.',
-        'E.A.',
-        'E.R.P.',
-        'Ed.D.',
-        'Ed.M.',
-        'Eng.D.',
-        'Esq.',
-        'F.B.C.S.',
-        'F.C.A.',
-        'F.C.C.A.',
-        'F.C.I.P.S.',
-        'F.C.M.I.',
-        'F.C.S.I.',
-        'F.I.E.T.',
-        'F.I.R.P.',
-        'F.Inst.L.M.',
-        'F.P.C.',
-        'F.R.M.',
-        'F.R.M.',
-        'G.S.P.',
-        'Hons.',
-        'I.F.R.S. Certified',
-        'I.T.I.L. v3',
-        'II',
-        'III',
-        'IV',
-        'J.D.',
-        'Jr.',
-        'K.C.',
-        'L.P.S.',
-        'LL.B.',
-        'LL.D.',
-        'LL.M.',
-        'M.A.',
-        'M.B.A.',
-        'M.B.E.',
-        'M.D.',
-        'M.E.P.',
-        'M.Ed.',
-        'M.Eng.',
-        'M.I.E.T.',
-        'M.Io.D.',
-        'M.Jur.',
-        'M.P.',
-        'M.P.A.',
-        'M.R.I.C.S.',
-        'M.S.',
-        'M.S.F.',
-        'M.S.F.S.',
-        'M.S.P.',
-        'M.Sc. D.',
-        'M.Sc.',
-        'O.B.E.',
-        'O.K.',
-        'O.R.S.C.',
-        'Oxon.',
-        'P.A.',
-        'P.C.C.',
-        'P.F.S.',
-        'P.H.R.',
-        'P.M.C.',
-        'P.M.P.',
-        'P.M.P.',
-        'P.S.P.',
-        'Ph.D.',
-        'Q.C.',
-        'R.D.',
-        'R.F.C.',
-        'R.I.C.P.',
-        'S.C.M.P',
-        'Sr.',
-        'T.M.I.E.T.',
-        'V',
-        'V.M.D.',
-      ],
-      organization: [
-        # These are sorted in length order: don't alphabetize them.
-        'S. de R.L. de C.V.',
-        'S.A.P.I. de C.V.',
-        'y. Cía. S. en C.',
-        'Private Limited',
-        'S.M. Pte. Ltd.',
-        'Cía. S. C. A.',
-        'y. Cía. S. C.',
-        'S.A. de C.V.',
-        'spol. s.r.o.',
-        '(Pty.) Ltd.',
-        '(Pvt.) Ltd.',
-        'A.D.S.I.Tz.',
-        'S.p. z.o.o.',
-        '(Pvt.)Ltd.',
-        'akc. spol.',
-        'Cía. Ltda.',
-        'E.B.V.B.A.',
-        'P. Limited',
-        'S. de R.L.',
-        'S.I.C.A.V.',
-        'S.P.R.L.U.',
-        'А.Д.С.И.Ц.',
-        '(P.) Ltd.',
-        'C. por A.',
-        'Comm.V.A.',
-        'Ltd. Şti.',
-        'Plc. Ltd.',
-        'Pte. Ltd.',
-        'Pty. Ltd.',
-        'Pvt. Ltd.',
-        'Soc. Col.',
-        'A.M.B.A.',
-        'A.S.B.L.',
-        'A.V.E.E.',
-        'B.V.B.A.',
-        'B.V.I.O.',
-        'C.V.B.A.',
-        'C.V.O.A.',
-        'E.E.I.G.',
-        'E.I.R.L.',
-        'E.O.O.D.',
-        'E.U.R.L.',
-        'F.M.B.A.',
-        'G.m.b.H.',
-        'Ges.b.R.',
-        'K.G.a.A.',
-        'L.L.L.P.',
-        'Ltd. Co.',
-        'Ltd. Co.',
-        'M.E.P.E.',
-        'n.y.r.t.',
-        'O.V.E.E.',
-        'P.E.E.C.',
-        'P.L.L.C.',
-        'P.L.L.C.',
-        'S. en C.',
-        'S.a.p.a.',
-        'S.A.R.L.',
-        'S.à.R.L.',
-        'S.A.S.U.',
-        'S.C.e.I.',
-        'S.C.O.P.',
-        'S.C.p.A.',
-        'S.C.R.I.',
-        'S.C.R.L.',
-        'S.M.B.A.',
-        'S.P.R.L.',
-        'Е.О.О.Д.',
-        '&. Cie.',
-        'and Co.',
-        'Comm.V.',
-        'Limited',
-        'P. Ltd.',
-        'Part.G.',
-        'Sh.p.k.',
-        '&. Co.',
-        'C.X.A.',
-        'd.n.o.',
-        'd.o.o.',
-        'E.A.D.',
-        'e.h.f.',
-        'E.P.E.',
-        'E.S.V.',
-        'F.C.P.',
-        'F.I.E.',
-        'G.b.R.',
-        'G.I.E.',
-        'G.M.K.',
-        'G.S.K.',
-        'H.U.F.',
-        'K.D.A.',
-        'k.f.t.',
-        'k.h.t.',
-        'k.k.t.',
-        'L.L.C.',
-        'L.L.P.',
-        'o.h.f.',
-        'O.H.G.',
-        'O.O.D.',
-        'O.y.j.',
-        'p.l.c.',
-        'P.S.U.',
-        'S.A.E.',
-        'S.A.S.',
-        'S.C.A.',
-        'S.C.E.',
-        'S.C.S.',
-        'S.E.M.',
-        'S.E.P.',
-        's.e.s.',
-        'S.G.R.',
-        'S.N.C.',
-        'S.p.A.',
-        'S.P.E.',
-        'S.R.L.',
-        's.r.o.',
-        'Unltd.',
-        'V.O.F.',
-        'V.o.G.',
-        'v.o.s.',
-        'V.Z.W.',
-        'z.r.t.',
-        'А.А.Т.',
-        'Е.А.Д.',
-        'З.А.Т.',
-        'К.Д.А.',
-        'О.О.Д.',
-        'Т.А.А.',
-        '股份有限公司',
-        'Ap.S.',
-        'Corp.',
-        'ltda.',
-        'Sh.A.',
-        'st.G.',
-        'Ultd.',
-        'a.b.',
-        'A.D.',
-        'A.E.',
-        'A.G.',
-        'A.S.',
-        'A.Ş.',
-        'A.y.',
-        'B.M.',
-        'b.t.',
-        'B.V.',
-        'C.A.',
-        'C.V.',
-        'd.d.',
-        'e.c.',
-        'E.E.',
-        'e.G.',
-        'E.I.',
-        'E.P.',
-        'E.T.',
-        'E.U.',
-        'e.v.',
-        'G.K.',
-        'G.P.',
-        'h.f.',
-        'Inc.',
-        'K.D.',
-        'K.G.',
-        'K.K.',
-        'k.s.',
-        'k.v.',
-        'K.y.',
-        'L.C.',
-        'L.P.',
-        'Ltd.',
-        'N.K.',
-        'N.L.',
-        'N.V.',
-        'O.E.',
-        'O.G.',
-        'O.Ü.',
-        'O.y.',
-        'P.C.',
-        'p.l.',
-        'Pty.',
-        'PUP.',
-        'Pvt.',
-        'r.t.',
-        'S.A.',
-        'S.D.',
-        'S.E.',
-        's.f.',
-        'S.L.',
-        'S.P.',
-        'S.s.',
-        'T.K.',
-        'T.Ü.',
-        'U.Ü.',
-        'Y.K.',
-        'А.Д.',
-        'І.П.',
-        'К.Д.',
-        'ПУП.',
-        'С.Д.',
-        'בע"מ',
-        '任意組合',
-        '匿名組合',
-        '合同会社',
-        '合名会社',
-        '合資会社',
-        '有限会社',
-        '有限公司',
-        '株式会社',
-        'A/S',
-        'G/S',
-        'I/S',
-        'K/S',
-        'P/S',
-        'S/A',
-      ],
+      person: get_constants_from('adfixes_suffix_person'),
+      organization: get_constants_from('adfixes_suffix_organization'),
       before: ADFIX_JOINERS, after: '\\z'
     },
   }.freeze
 
-  ADFIX_PATTERNS = Hash[%i[prefix suffix].map do |adfix_type|
+  CONTACT_TYPES = %i[person organization].freeze
+
+  ADFIX_PATTERNS = %i[prefix suffix].to_h do |adfix_type|
     patterns = {}
     adfix = ADFIXES[adfix_type]
 
-    %i[person organization].each do |ct|
+    CONTACT_TYPES.each do |ct|
       with_optional_spaces = adfix[ct].map { |p| p.gsub(ASCII_SPACE, ' *') }
       pattern_string = with_optional_spaces.join('|').gsub('.', '\.*')
-      patterns[ct] = /#{adfix[:before]}\(*(?:#{pattern_string})[®™\)]*#{adfix[:after]}/i
+      patterns[ct] = /#{adfix[:before]}\(*(?:#{pattern_string})[®™)]*#{adfix[:after]}/i
     end
 
     [adfix_type, patterns]
-  end]
+  end
 end

data/lib/name_tamer/name/private_methods_nice_name.rb

@@ -0,0 +1,116 @@
+# frozen_string_literal: true
+
+module NameTamer
+  class Name
+    module PrivateMethodsNiceName
+      def unescape
+        @tidy_name = Strings.unescape_html(Strings.safe_unescape(Strings.ensure_safe(@tidy_name)))
+      end
+
+      def remove_zero_width
+        @tidy_name = Strings.strip_unwanted(@tidy_name, ZERO_WIDTH_FILTER)
+      end
+
+      def tidy_spacing
+        @tidy_name = Strings.whitespace_to(Strings.space_around_comma(@tidy_name).strip, ASCII_SPACE)
+      end
+
+      def fix_encoding_errors
+        @tidy_name = Strings.fix_encoding_errors(@tidy_name)
+      end
+
+      # Remove spaces from groups of initials
+      def consolidate_initials
+        @tidy_name = Strings.ensure_space_after_initials(Strings.remove_spaces_from_initials(@tidy_name))
+      end
+
+      # An adfix is either a prefix or a suffix
+      def remove_adfixes
+        if @last_name.nil?
+          # Our name is still in one part, not two
+          loop do
+            @nice_name = remove_outermost_adfix(:suffix, @nice_name)
+            break unless @adfix_found
+          end
+
+          loop do
+            @nice_name = remove_outermost_adfix(:prefix, @nice_name)
+            break unless @adfix_found
+          end
+        else
+          # Our name is currently in two halves
+          loop do
+            @last_name = remove_outermost_adfix(:suffix, @last_name)
+            break unless @adfix_found
+          end
+
+          loop do
+            @remainder = remove_outermost_adfix(:prefix, @remainder)
+            break unless @adfix_found
+          end
+        end
+      end
+
+      # Names in the form "Smith, John" need to be turned around to "John Smith"
+      def fixup_last_name_first
+        return if @contact_type == :organization
+
+        parts = @nice_name.split ', '
+
+        return unless parts.count == 2
+
+        @last_name = parts[0] # Sometimes the last name alone is all caps and we can name-case it
+        @remainder = parts[1]
+      end
+
+      # Sometimes we end up with mismatched braces after adfix stripping
+      # e.g. "Ceres (Ceres Holdings LLC)" -> "Ceres (Ceres Holdings"
+      def fixup_mismatched_braces
+        left_brace_count = @nice_name.count '('
+        right_brace_count = @nice_name.count ')'
+
+        if left_brace_count > right_brace_count
+          @nice_name += ')'
+        elsif left_brace_count < right_brace_count
+          @nice_name = "(#{@nice_name}"
+        end
+      end
+
+      def name_wrangle
+        # Fix case if all caps or all lowercase
+        if @last_name.nil?
+          name_wrangle_single_name
+        else
+          name_wrangle_split_name
+        end
+      end
+
+      def name_wrangle_single_name
+        lowercase = @nice_name.downcase
+        uppercase = @nice_name.upcase
+        fix_case = false
+
+        if @contact_type == :organization
+          fix_case = true if @nice_name == uppercase && @nice_name.length > 4
+        elsif [uppercase, lowercase].include?(@nice_name)
+          fix_case = true
+        end
+
+        @nice_name = name_case(lowercase) if fix_case
+      end
+
+      def name_wrangle_split_name
+        # It's a person if we've split the name, so no organization logic here
+        lowercase = @last_name.downcase
+        uppercase = @last_name.upcase
+        @last_name = name_case(lowercase) if [uppercase, lowercase].include?(@last_name)
+        @nice_name = "#{@remainder} #{@last_name}"
+      end
+
+      # Conjoin compound names with non-breaking spaces
+      def use_nonbreaking_spaces_in_compound_names
+        @nice_name = Strings.nbsp_in_name_modifier(Strings.nbsp_in_compound_name(@nice_name))
+      end
+    end
+  end
+end

data/lib/name_tamer/name/private_methods_simple_name.rb

@@ -0,0 +1,71 @@
+# frozen_string_literal: true
+
+module NameTamer
+  class Name
+    module PrivateMethodsSimpleName
+      # Remove initials from personal names unless they are the only identifier.
+      # i.e. only remove initials if there's also a proper name there
+      def remove_initials
+        return unless @contact_type == :person
+
+        temp_name = @simple_name.gsub(/\b([a-z](?:\.*\s+|\.))/i, '')
+
+        # If the name still has at least one space we're OK
+        @simple_name = temp_name if temp_name.include?(ASCII_SPACE)
+      end
+
+      def remove_middle_names
+        return unless @contact_type == :person
+
+        first_name, parts = find_first_usable_name(@simple_name.split)
+        last_name, = find_last_usable_name(parts)
+
+        return unless first_name || last_name
+
+        separator = first_name && last_name ? ' ' : ''
+        @simple_name = "#{first_name}#{separator}#{last_name}"
+      end
+
+      def find_first_usable_name(parts)
+        part = nil
+
+        parts.each_index do |i|
+          part = parts[i]
+          next if part.gsub(FILTER_COMPAT, '').empty?
+
+          parts = parts.slice(i + 1, parts.length) # don't use "slice!"
+          break
+        end
+
+        [part, parts]
+      end
+
+      def find_last_usable_name(parts)
+        part = nil
+
+        parts.reverse_each do |p|
+          next if p.gsub(FILTER_COMPAT, '').empty?
+
+          part = p
+          break
+        end
+
+        part
+      end
+
+      def remove_periods_from_initials
+        @simple_name = Strings.remove_periods_from_initials(@simple_name)
+      end
+
+      def standardize_words
+        words = @simple_name
+                .gsub(/ *& */, ' and ') # replace ampersand characters with ' and '
+                .gsub(/ *\+ */, ' plus ') # replace plus signs with ' plus '
+                .gsub(/\bintl\b/i, 'International') # replace 'intl' with 'International'
+                .gsub(/[־‐‑‒–—―−﹘﹣－]/, SLUG_DELIMITER) # Replace Unicode dashes with ASCII hyphen
+
+        @simple_name = Strings.strip_unwanted(words, /["“”™℠®©℗]/) # remove quotes and commercial decoration
+      end
+    end
+  end
+end