name_tamer 0.6.0 → 0.6.1

data/lib/name_tamer/name.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module NameTamer
   class Name
     # References:
@@ -215,7 +217,7 @@ module NameTamer
       lowercase = @last_name.downcase
       uppercase = @last_name.upcase
       @last_name = name_case(lowercase) if [uppercase, lowercase].include?(@last_name)
-      @nice_name = "#{@remainder} #{@last_name}"
+      @nice_name = +"#{@remainder} #{@last_name}"
     end
 
     # Conjoin compound names with non-breaking spaces
@@ -249,7 +251,7 @@ module NameTamer
       return unless first_name || last_name
 
       separator = first_name && last_name ? ' ' : ''
-      @simple_name = "#{first_name}#{separator}#{last_name}"
+      @simple_name = +"#{first_name}#{separator}#{last_name}"
     end
 
     def find_first_usable_name(parts)

data/lib/name_tamer/string.rb

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# frozen_string_literal: true
 
 class String
   unless respond_to? :presence
@@ -23,7 +23,8 @@ class String
 
   # Ensure commas have exactly one space after them
   def space_around_comma!
-    substitute!(/[[:space:]]*,[[:space:]]*/, ', ')
+    substitute!(/[[:space:]]*,[[:space:]]*/, ',
+    ')
   end
 
   # Change some characters embedded in words to our separator character
@@ -36,10 +37,7 @@ class String
   # 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
+    string = CGI.unescape(gsub('+', '%2B'))
     return self if self == string
     replace string
     ensure_safe!
@@ -177,51 +175,240 @@ class String
     gsub!(pattern, replacement) || self
   end
 
-  NONBREAKING_SPACE = "\u00a0".freeze
-  ASCII_SPACE = ' '.freeze
+  NONBREAKING_SPACE = "\u00a0"
+  ASCII_SPACE = ' '
 
   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'
+    # 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
 
   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'
+    'Al',
+    'Ap',
+    'Ben',
+    'D[aeiou]',
+    'D[ao]s',
+    'De[lrn]',
+    'Dell[ae]',
+    'El',
+    'L[eo]',
+    'La',
+    'Of',
+    'San',
+    'St[\.]?',
+    'V[ao]n',
+    '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'
+    'İ' => 'I',
+    '×' => 'x',
+    'ß' => 'ss',
+    'À' => 'A',
+    'à' => 'a',
+    'Á' => 'A',
+    'á' => 'a',
+    'Â' => 'A',
+    'â' => 'a',
+    'Ã' => 'A',
+    'ã' => 'a',
+    'Ä' => 'A',
+    'ä' => 'a',
+    'Å' => 'A',
+    'å' => 'a',
+    'Æ' => 'AE',
+    'æ' => 'ae',
+    'Ç' => 'C',
+    'ç' => 'c',
+    'È' => 'E',
+    'è' => 'e',
+    'É' => 'E',
+    'é' => 'e',
+    'Ê' => 'E',
+    'ê' => 'e',
+    'Ë' => 'E',
+    'ë' => 'e',
+    'Ì' => 'I',
+    'ì' => 'i',
+    'Í' => 'I',
+    'í' => 'i',
+    'Î' => 'I',
+    'î' => 'i',
+    'Ï' => 'I',
+    'ï' => 'i',
+    'Ð' => 'D',
+    'ð' => 'd',
+    'Ñ' => 'N',
+    'ñ' => 'n',
+    'Ò' => 'O',
+    'ò' => 'o',
+    'Ó' => 'O',
+    'ó' => 'o',
+    'Ô' => 'O',
+    'ô' => 'o',
+    'Õ' => 'O',
+    'õ' => 'o',
+    'Ö' => 'O',
+    'ö' => 'o',
+    'Ø' => 'O',
+    'ø' => 'o',
+    'Ù' => 'U',
+    'ù' => 'u',
+    'Ú' => 'U',
+    'ú' => 'u',
+    'Û' => 'U',
+    'û' => 'u',
+    'Ü' => 'U',
+    'ü' => 'u',
+    'Ý' => 'Y',
+    'ý' => 'y',
+    'Þ' => 'Th',
+    'þ' => 'th',
+    'ÿ' => 'y',
+    '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',
+    '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',
+    'Ź' => 'Z',
+    'ź' => 'z',
+    'Ż' => 'Z',
+    'ż' => 'z',
+    'ž' => 'z',
+    'Ž' => 'Z',
   }.freeze
 
   # When strings are mistakenly encoded as single-byte character sets, instead
@@ -229,34 +416,130 @@ class String
   # 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', '‘' => '‘', '’' => '’',
-    '“' => '“',
+    "\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
-    '•' => '•', '–' => '–', '—' => '—',
-    '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',
+    '‹' => '‹',
+    '›' => '›',
+    '“' => '“',
+    '‚' => '‚',
+    '„' => '„',
+    '‘' => '‘',
+    '–' => '–',
+    '—' => '—',
+    '’' => '’',
+    '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�' => 'Á',
+    '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