icu_name 0.1.2 → 0.1.3

data/README.rdoc

@@ -26,24 +26,30 @@ Capitalisation, white space and punctuation will all be automatically corrected:
   robert.name                                             # => 'Robert J. Fischer'
   robert.rname                                            # => 'Fischer, Robert J.'  (reversed name)
 
-The input text, without any changes apart from white-space cleanup, is returned by the _original_ method:
+The input text, without any changes apart from white-space cleanup and the insertion of a comma
+(to separate the two names), is returned by the _original_ method:
 
-  robert.original                                         # => 'robert j FISHER'
+  robert.original                                         # => 'FISCHER, robert j'
 
 To avoid ambiguity when either the first or second names consist of multiple words, it is better to
 supply the two separately, if known. However, the full name can be supplied alone to the constructor
-and a guess will be made as to the first and last names.
+and a guess will be made as to the first and last names (the last distinct word becomes the last name).
 
-  bobby = ICU::Name.new(' bobby fischer ')
+  bobby = ICU::Name.new(' bobby  fischer ')
 
   bobby.first                                             # => 'Bobby'
   bobby.last                                              # => 'Fischer'
 
+But in this case, since the names were not supplied separately, the _original_ text will not contain a comma:
+
+  bobby.original                                          # => 'bobby fischer'
+
 Names will match even if one is missing middle initials or if a nickname is used for one of the first names.
 
   bobby.match('Robert J.', 'Fischer')                     # => true
 
-Note that the class is aware of only common nicknames (e.g. _Bobby_ and _Robert_, _Bill_ and _William_, etc), not all possibilities.
+Note that the class is aware of only common nicknames (e.g. _Bobby_ and _Robert_, _Bill_ and _William_, etc)
+and not all possibilities.
 
 Supplying the _match_ method with strings is equivalent to instantiating a Name instance with the same
 strings and then matching it. So, for example the following are equivalent:
@@ -80,14 +86,14 @@ strings encoded in UTF-8, no matter what the input encoding.
   eric = ICU::Name.new('éric'.encode("ISO-8859-1"), 'PRIÉ'.force_encoding("ASCII-8BIT"))
   eric.rname                                              # => "Prié, Éric"
   eric.rname.encoding.name                                # => "UTF-8"
-  eric.original                                           # => "éric PRIÉ"
+  eric.original                                           # => "PRIÉ, éric"
   eric.original.encoding.name                             # => "UTF-8"
 
 Accented letters can be transliterated into their US-ASCII counterparts by setting the
 _chars_ option, which is available in all accessors. For example:
 
   eric.rname(:chars => "US-ASCII")                        # => "Prie, Eric"
-  eric.original(:chars => "US-ASCII")                     # => "eric PRIE"
+  eric.original(:chars => "US-ASCII")                     # => "PRIE, eric"
 
 Also possible is the preservation of ISO-8859-1 characters, but the transliteration of
 all other accented characters:

data/lib/icu_name/name.rb

@@ -66,7 +66,7 @@ module ICU
 
     # Save the original inputs without any cleanup other than whitespace.
     def originalize
-      @original = "#{@name1} #{@name2}"
+      @original = @name2 == '' ? @name1.clone : "#{@name2.strip}, #{@name1.strip}"
       @original.strip!
       @original.gsub!(/\s+/, ' ')
     end

data/lib/icu_name/version.rb

@@ -2,6 +2,6 @@
 
 module ICU
   class Name
-    VERSION = "0.1.2"
+    VERSION = "0.1.3"
   end
 end

data/spec/name_spec.rb

@@ -29,7 +29,7 @@ module ICU
       end
 
       it "#original returns the original data" do
-        @simple.original.should == 'mark j l ORR'
+        @simple.original.should == 'ORR, mark j l'
       end
 
       it "#match returns true if and only if two names match" do
@@ -72,10 +72,10 @@ module ICU
         eric = Name.new('éric'.encode("ISO-8859-1"), 'PRIÉ'.force_encoding("ASCII-8BIT"))
         eric.rname.should == "Prié, Éric"
         eric.rname.encoding.name.should == "UTF-8"
-        eric.original.should == "éric PRIÉ"
+        eric.original.should == "PRIÉ, éric"
         eric.original.encoding.name.should == "UTF-8"
         eric.rname(:chars => "US-ASCII").should == "Prie, Eric"
-        eric.original(:chars => "US-ASCII").should == "eric PRIE"
+        eric.original(:chars => "US-ASCII").should == "PRIE, eric"
         joe = Name.new('Józef', 'Żabiński')
         joe.rname.should == "Żabiński, Józef"
         joe.rname(:chars => "ISO-8859-1").should == "Zabinski, Józef"
@@ -183,8 +183,9 @@ module ICU
 
     context "the original input" do
       it "should be the original text unaltered except for white space" do
-        Name.new(' Mark   j l   ', ' ORR  ').original.should == 'Mark j l ORR'
-        Name.new('Józef', 'Żabiński').original.should == 'Józef Żabiński'
+        Name.new(' Mark   j l   ', ' ORR  ').original.should == 'ORR, Mark j l'
+        Name.new(' Mark  J.  L.  Orr ').original.should == 'Mark J. L. Orr'
+        Name.new('Józef', 'Żabiński').original.should == 'Żabiński, Józef'
         Name.new('Ui  Laigleis,Gearoidin').original.should == 'Ui Laigleis,Gearoidin'
       end
     end

metadata

@@ -5,8 +5,8 @@ version: !ruby/object:Gem::Version
   segments: 
   - 0
   - 1
-  - 2
-  version: 0.1.2
+  - 3
+  version: 0.1.3
 platform: ruby
 authors: 
 - Mark Orr
@@ -14,7 +14,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-02-12 00:00:00 +00:00
+date: 2011-02-19 00:00:00 +00:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency