name-tamer 0.1.6 → 0.1.7

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 2706fda214e230fdf9bda63cc4424842183672e3
-  data.tar.gz: 89f191da4268cfbca81674335e3dfe5abec626a0
+  metadata.gz: f8e5bd6a935818948438315fc5f7a1a2ff90e173
+  data.tar.gz: c6b2f73fa732939faa8e0eef6c680d852374b7c2
 SHA512:
-  metadata.gz: cc8d7e0474059fe5e3680cc720655c303628fbb1ea25fe638e2e630582374720dd867b1b149c18990503d2c7e3d68ead42b896f41331c2fc650f13287146e438
-  data.tar.gz: 16e081e040d86117620e5a1760e8cf49328264adf9488ab29f3f8649d4e732247f30b4ed430005bd5ba51063ce03d196728e9323e0b1b300912dd32993282de8
+  metadata.gz: dca80914cdbb4d1e6d254e51c2c9104ea18410424cd75663800564ac9c597cfe19c16651467cebc20883f4359b9e394ee23fbc0291cd6dad293c801db862ec84
+  data.tar.gz: 4cfadfe895919caf36468c5dc2c243054db0be686f8a6bb8500c69f4f7b39aeb00e9c32e6d358eb088e6e39c36ce1f9eb2d3d2ebce5806f5618aa8ee41832b75

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    name-tamer (0.1.5)
+    name-tamer (0.1.6)
 
 GEM
   remote: https://rubygems.org/

data/lib/name-tamer.rb

@@ -26,6 +26,7 @@ class NameTamer
       @nice_name = name.dup          # Start with the name we've received
 
       tidy_spacing                    # " John   Smith " -> "John Smith"
+      fix_encoding_errors             # "René Descartes" -> "René Descartes"
       consolidate_initials            # "I. B. M." -> "I.B.M."
       remove_adfixes                  # prefixes and suffixes: "Smith, John, Jr." -> "Smith, John"
       fixup_last_name_first           # "Smith, John" -> "John Smith"
@@ -108,6 +109,10 @@ class NameTamer
       .whitespace_to!(ASCII_SPACE)
   end
 
+  def fix_encoding_errors
+    @nice_name.fix_encoding_errors!
+  end
+
   # Remove spaces from groups of initials
   def consolidate_initials
     @nice_name

data/lib/name-tamer/version.rb

@@ -1,3 +1,3 @@
 class NameTamer
-  VERSION = '0.1.6'
+  VERSION = '0.1.7'
 end

data/lib/string_extras.rb

@@ -51,6 +51,13 @@ class String
     self # Allows chaining
   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!
+    self.gsub!(BAD_ENCODING_PATTERNS) { |substring| BAD_ENCODING[substring] || substring }
+    self # Allows chaining
+  end
+
   def upcase_first_letter!
     self.gsub!(/\b\w/) { |first| first.upcase }
     self # Allows chaining
@@ -190,4 +197,37 @@ class String
     'Ŷ' => 'Y', 'ŷ' => 'y', 'Ÿ' => 'Y', 'Ź' => 'Z', 'ź' => 'z', 'Ż' => 'Z', 'ż' => 'z',
     'Ž' => 'Z', 'ž' => 'z'
   }
+
+  # 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
+  BAD_ENCODING = {
+    '€' => '€', '‚' => '‚', 'Æ’' => 'ƒ', '„' => '„', '…' => '…',
+    'â€' => '†', '‡' => '‡', 'ˆ' => 'ˆ', '‰' => '‰', 'Å ' => 'Š',
+    '‹' => '‹', 'Å’' => 'Œ', 'Ž' => 'Ž', '‘' => '‘', '’' => '’',
+    '“' => '“', 'â€' => '”', '•' => '•', '–' => '–', '—' => '—',
+    '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', 'Ã�' => 'Í', 'ÃŽ' => 'Î', 'Ã�' => 'Ï',
+    'Ã�' => 'Ð', 'Ñ' => 'Ñ', 'Ã’' => 'Ò', 'Ó' => 'Ó', 'Ô' => 'Ô',
+    'Õ' => 'Õ', 'Ö' => 'Ö', '×' => '×', 'Ø' => 'Ø', 'Ù' => 'Ù',
+    'Ú' => 'Ú', 'Û' => 'Û', 'Ãœ' => 'Ü', 'Ã�' => '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'
+  }
+
+  BAD_ENCODING_PATTERNS = /(#{BAD_ENCODING.keys.join('|')})/
 end

data/spec/name_tamer_spec.rb

@@ -181,6 +181,12 @@ describe NameTamer do
         nn: 'Scout® Loyalty Optimizer',
         sn: 'Scout Loyalty Optimizer',
         s: 'scout-loyalty-optimizer'
+      },
+      { n: 'René Descartes',
+        t: :person,
+        nn: 'René Descartes',
+        sn: 'René Descartes',
+        s:'rene-descartes'
       }
     ]
   end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: name-tamer
 version: !ruby/object:Gem::Version
-  version: 0.1.6
+  version: 0.1.7
 platform: ruby
 authors:
 - Xenapto