name-tamer 0.1.9 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: b556d5a36fcb89c56e435fd67a0f159987b7f8b9
-  data.tar.gz: 7ac8e5b948e6edb607f367d4d8303bb3c97c0d9d
+  metadata.gz: 3532b7472b3daecb0bb11863268531c229771639
+  data.tar.gz: 0096dd16106d480f6c5e1e043dbf54896f787599
 SHA512:
-  metadata.gz: 215966db363f5630a1b53671c95792057deb29306a07e1cf93c1772700be4b3fc3e4f9cab40a1ba6d39f58813eddead3226d1faa2583aa21e3d73f41eb2c1403
-  data.tar.gz: 4d2bcd7d0f9b8556c548235c4d12ae0c92643399444a2ce70c5e9b8ef984577d54915827a86f4b243d3434775a1ddb37ccd1d0055b8645c56ab770bdba558613
+  metadata.gz: 4ee6d017e93b54acd10791f44a2920c46fe76faaafcb0171ab59c582f7d07c34036bc64610c5298ae363a33fa26fbedd1711800771acc29620beb6967adea10e
+  data.tar.gz: 23741e994c62fc8c746f826e3124824a29e3a5ecff22930a1ec350db0363b5b6d20d67bc5104d546f25c9301850a8944e936cb5e41c6320524d766303a2be69c

data/.rubocop.yml

@@ -7,4 +7,4 @@ CyclomaticComplexity:
 ClassLength:
   Description: 'Avoid classes longer than 100 lines of code.'
   CountComments: false  # count full line comments?
-  Max: 316
+  Max: 321

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    name-tamer (0.1.8)
+    name-tamer (0.1.9)
 
 GEM
   remote: https://rubygems.org/

data/lib/name-tamer.rb

@@ -23,11 +23,12 @@ class NameTamer
 
   def tidy_name
     unless @tidy_name
-      @tidy_name = name.dup          # Start with the name we've received
+      @tidy_name = name.dup # Start with the name we've received
 
-      tidy_spacing                    # " John   Smith " -> "John Smith"
-      fix_encoding_errors             # "Ren\u00c3\u00a9 Descartes" -> "Ren\u00e9 Descartes"
-      consolidate_initials            # "I. B. M." -> "I.B.M."
+      ensure_safe           # Invalid byte sequence in UTF-8, for example
+      tidy_spacing          # " John   Smith " -> "John Smith"
+      fix_encoding_errors   # "Ren\u00c3\u00a9 Descartes" -> "Ren\u00e9 Descartes"
+      consolidate_initials  # "I. B. M." -> "I.B.M."
     end
 
     @tidy_name
@@ -111,6 +112,10 @@ class NameTamer
   # Tidy up the name we've received
   #--------------------------------------------------------
 
+  def ensure_safe
+    @tidy_name.ensure_safe
+  end
+
   def tidy_spacing
     @tidy_name
       .space_after_comma!
@@ -295,6 +300,7 @@ class NameTamer
       @contact_type = ct
     end
 
+    @tidy_name    = nil
     @nice_name    = nil
     @simple_name  = nil
     @slug         = nil

data/lib/name-tamer/version.rb

@@ -1,3 +1,3 @@
 class NameTamer
-  VERSION = '0.1.9'
+  VERSION = '0.2.0'
 end

data/lib/string_extras.rb

@@ -2,83 +2,74 @@
 class String
   # Strip illegal characters out completely
   def strip_unwanted!(filter)
-    self.gsub!(filter, '')
-    self # Allows chaining
+    substitute!(filter, '')
   end
 
   def strip_or_self!
-    self.strip!
-    self # Allows chaining
+    strip! || self
   end
 
   # Change any whitespace into our separator character
   def whitespace_to!(separator)
-    self.gsub!(/[[:space:]]+/, separator)
-    self # Allows chaining
+    substitute!(/[[:space:]]+/, separator)
   end
 
   # Ensure commas have exactly one space after them
   def space_after_comma!
-    self.gsub!(/,[[:space:]]*/, ', ')
-    self # Allows chaining
+    substitute!(/,[[:space:]]*/, ', ')
   end
 
   # Change some characters embedded in words to our separator character
   # e.g. example.com -> example-com
   def invalid_chars_to!(separator)
-    self.gsub!(/(?<![[:space:]])[\.\/](?![[:space:]])/, separator)
-    self # Allows chaining
+    substitute!(/(?<![[:space:]])[\.\/](?![[:space:]])/, separator)
   end
 
   # Make sure separators are not where they shouldn't be
   def fix_separators!(separator)
-    unless separator.nil? || separator.empty?
-      r = Regexp.escape(separator)
-      # No more than one of the separator in a row.
-      self.gsub!(/#{r}{2,}/, separator)
-      # Remove leading/trailing separator.
-      self.gsub!(/^#{r}|#{r}$/i, '')
-    end
+    return self if separator.nil? || separator.empty?
 
-    self # Allows chaining
+    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!
-    self.gsub!(/[^\x00-\x7f]/u) { |char| APPROXIMATIONS[char] || char }
-    self # Allows chaining
+    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!
-    self.gsub!(BAD_ENCODING_PATTERNS) { |substring| BAD_ENCODING[substring] || substring }
-    self # Allows chaining
+    gsub!(BAD_ENCODING_PATTERNS) { |substring| BAD_ENCODING[substring] || substring } || self
   end
 
   def upcase_first_letter!
-    self.gsub!(/\b\w/) { |first| first.upcase }
-    self # Allows chaining
+    gsub!(/\b\w/) { |first| first.upcase } || self
   end
 
   def downcase_after_apostrophe!
-    self.gsub!(/\'\w\b/) { |c| c.downcase } # Lowercase 's
-    self # Allows chaining
+    gsub!(/\'\w\b/) { |c| c.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/
-      self.gsub!(/\b(Ma?c)([A-Za-z]+)/) { |_| Regexp.last_match[1] + Regexp.last_match[2].capitalize }
+      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| self.gsub!(/\b#{mac_name}/, mac_name.capitalize) }
+      ).each { |mac_name| substitute!(/\b#{mac_name}/, mac_name.capitalize) }
     end
 
     self # Allows chaining
@@ -88,7 +79,7 @@ class String
   def fix_ff!
     %w(
       Fforbes Fforde Ffinch Ffrench Ffoulkes
-    ).each { |ff_name| self.gsub!(ff_name, ff_name.downcase) }
+    ).each { |ff_name| substitute!(ff_name, ff_name.downcase) }
 
     self # Allows chaining
   end
@@ -98,13 +89,13 @@ class String
   # Fixes for name modifiers followed by an apostrophe, e.g. d'Artagnan, Commedia dell'Arte
   def fix_name_modifiers!
     NAME_MODIFIERS.each do |modifier|
-      self.gsub!(/((?:[[:space:]]|^)#{modifier})([[:space:]]+|-)/) do |_|
+      gsub!(/((?:[[:space:]]|^)#{modifier})([[:space:]]+|-)/) do |_|
         "#{Regexp.last_match[1].rstrip.downcase}#{Regexp.last_match[2].tr(ASCII_SPACE, NONBREAKING_SPACE)}"
       end
     end
 
     %w(Dell D).each do |modifier|
-      self.gsub!(/(.#{modifier}')(\w)/) { |_| "#{Regexp.last_match[1].rstrip.downcase}#{Regexp.last_match[2]}" }
+      gsub!(/(.#{modifier}')(\w)/) { |_| "#{Regexp.last_match[1].rstrip.downcase}#{Regexp.last_match[2]}" }
     end
 
     self # Allows chaining
@@ -113,16 +104,14 @@ class String
   # Upcase words with no vowels, e.g JPR Williams
   # Except Ng
   def upcase_initials!
-    self.gsub!(/\b([bcdfghjklmnpqrstvwxz]+)\b/i) { |_| Regexp.last_match[1].upcase }
-    self.gsub!(/\b(NG)\b/i) { |_| Regexp.last_match[1].capitalize } # http://en.wikipedia.org/wiki/Ng
-
-    self # Allows chaining
+    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|
-      self.gsub!(compound_name, compound_name.tr(ASCII_SPACE, NONBREAKING_SPACE))
+      substitute!(compound_name, compound_name.tr(ASCII_SPACE, NONBREAKING_SPACE))
     end
 
     self # Allows chaining
@@ -130,25 +119,33 @@ class String
 
   def nbsp_in_name_modifier!
     NAME_MODIFIERS.each do |modifier|
-      self.gsub!(/([[:space:]]#{modifier})([[:space:]])/i) { |_| "#{Regexp.last_match[1]}#{NONBREAKING_SPACE}" }
+      gsub!(/([[:space:]]#{modifier})([[:space:]])/i) { |_| "#{Regexp.last_match[1]}#{NONBREAKING_SPACE}" }
     end
 
     self # Allows chaining
   end
 
   def remove_periods_from_initials!
-    self.gsub!(/\b([a-z])\./i) { |_| Regexp.last_match[1] }
-    self # Allows chaining
+    gsub!(/\b([a-z])\./i) { |_| Regexp.last_match[1] } || self
   end
 
   def remove_spaces_from_initials!
-    self.gsub!(/\b([a-z])(\.)* \b(?![a-z0-9']{2,})/i) { |_| "#{Regexp.last_match[1]}#{Regexp.last_match[2]}" }
-    self # Allows chaining
+    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!
-    self.gsub!(/\b([a-z]\.)(?=[a-z0-9]{2,})/i) { |_| "#{Regexp.last_match[1]} " }
-    self # Allows chaining
+    gsub!(/\b([a-z]\.)(?=[a-z0-9]{2,})/i) { |_| "#{Regexp.last_match[1]} " } || self
+  end
+
+  def ensure_safe
+    return if valid_encoding?
+    encode!('UTF-8', invalid: :replace, undef: :replace, replace: '')
+  end
+
+  def substitute!(pattern, replacement)
+    gsub!(pattern, replacement) || self
   end
 
   NONBREAKING_SPACE = "\u00a0"

data/spec/name_tamer_spec.rb

@@ -183,12 +183,9 @@ describe NameTamer do
         sn: 'Scout Loyalty Optimizer',
         s: 'scout-loyalty-optimizer'
       },
-      { n: 'René Descartes',
-        t: :person,
-        nn: 'René Descartes',
-        sn: 'René Descartes',
-        s: 'rene-descartes'
-      }
+      { n: 'René Descartes', t: :person, nn: 'René Descartes', sn: 'René Descartes', s: 'rene-descartes' },
+      { n: 'Pablo M Sánchez', t: :person, nn: 'Pablo M Sánchez', sn: 'Pablo Sánchez', s: 'pablo-sanchez' },
+      { n: "\xc3\x28", t: :person, nn: '()', sn: '()', s: '_' } # Invalid byte sequence in UTF-8
     ]
   end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: name-tamer
 version: !ruby/object:Gem::Version
-  version: 0.1.9
+  version: 0.2.0
 platform: ruby
 authors:
 - Xenapto
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-06-30 00:00:00.000000000 Z
+date: 2014-07-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler