japanese_names 0.0.1 → 0.0.2

checksums.yaml

@@ -1,15 +1,15 @@
 ---
 !binary "U0hBMQ==":
   metadata.gz: !binary |-
-    MmIzYzM1YThjMjlkZGNmMWM4Y2NjNmZkZWY2Y2EzMWQ3MmQyMTkyNg==
+    Y2RiZjRlZTEzMDQ4NjJhZmQyMTg4YmI5ZjE0M2IyNGU5MGRlNGU1YQ==
   data.tar.gz: !binary |-
-    NzRkNTIxOWIzZDY4NzA2MmQyYjIxNmExMTI5ZmY0ZWUxMGNlMTdjNw==
+    OWVlN2EzY2NmYWNiMzA1ZThjZGQxYjUxY2MwZTE2YzRhZGZiNDU5ZA==
 SHA512:
   metadata.gz: !binary |-
-    YTdlMGM4OGRmOGNiMTQzNWFiMDkxZmFkZDQ1MzJhZmI5YjEzZmIzZTgxMDIw
-    ZWU5OWU0N2NjMWUxYTQwMzBiYTc3N2QyNThhZDM1NmYwZjk1MDc1ODhkODA2
-    MWIyM2ZlMjIzOGFjNTA2NWNiYmExMTUxNGRmZGE4ZTcwMmQ0ODU=
+    YmViZDBkNzFhNjU5OGE0NGNlZDAzMzUzMTAwZjBmOWI3OWE3ZjdhZjYwYTI4
+    MDZlODJkNTA2ZjQ5ZTU2M2E2YjEwNzY1Mjk2MDVlOWMyNWU4NzA4ZTlkNmFl
+    MTlkZjdhNjhhY2NiZDQ3MTU3MjQ3MTMzMmVjMTE2YTg5NmM4YzM=
   data.tar.gz: !binary |-
-    MmQ0MGJiNDA0OGJmNDk1ZmNmNmIyYjNmM2Q1NjYxN2JmNjBiOWZiZjRkMDBj
-    YmVhYTdkNDQ1NGNhNDIyMDgyODU4YTFlYWJiOTlhZjM3ODEwOGJlOGI3ZWFi
-    ODhkODc4ZWM2MWExZmZkYmJhYzk2Y2RlNGM5ZGE0N2YxZDc1Mzg=
+    ZTVmZWI4ZGUxNDQ5ZDA5ZTZhYjRkZjcxMzU3ZDQxNmQ2YTYwMmQyZTk3Njgz
+    NzUxYzdlOThkNTgwM2I4NGQxODY5OWMxNGM3OGIwODViYmU1ZjZjYmIzZWNi
+    YjhhOWIzMDM2ZjFhNDhlMjZlM2I3MjFjYjdlNGYxYmU0NzM0NGE=

data/lib/japanese_names/parser.rb

@@ -18,6 +18,8 @@ module JapaneseNames
     end
 
     def split_giv(kanji, kana)
+      return nil unless kanji && kana
+      kanji, kana = kanji.strip, kana.strip
       dict = Enamdict.match(kanji: window_right(kanji))
       dict.sort!{|x,y| y[0].size <=> x[0].size}
       kana_match = nil
@@ -27,6 +29,8 @@ module JapaneseNames
     end
 
     def split_fam(kanji, kana)
+      return nil unless kanji && kana
+      kanji, kana = kanji.strip, kana.strip
       dict = Enamdict.match(kanji: window_left(kanji))
       dict.sort!{|x,y| y[0].size <=> x[0].size}
       kana_match = nil
@@ -61,16 +65,16 @@ module JapaneseNames
 
     # Given a String, returns an array of progressively smaller substrings anchored on the left side.
     #
-    # Example: window_left("abcde") #=>  ["abcd", "abc", "ab", "a"]
+    # Example: window_left("abcd")  #=> ["abcd", "abc", "ab", "a"]
     def window_left(str)
-      (0..str.size-2).to_a.reverse.map{|i| str[0..i]}
+      (0...str.size).to_a.reverse.map{|i| str[0..i]}
     end
 
     # Given a String, returns an array of progressively smaller substrings anchored on the right side.
     #
-    # Example: window_right("abcde") #=>  ["bcde", "cde", "de", "e"]
+    # Example: window_right("abcd")  #=> ["abcd", "bcd", "cd", "d"]
     def window_right(str)
-      (1..str.size-1).map{|i| str[i..-1]}
+      (0...str.size).map{|i| str[i..-1]}
     end
   end
 end

data/lib/japanese_names/version.rb

@@ -2,5 +2,5 @@
 # encoding: utf-8
 
 module JapaneseNames
-  VERSION = '0.0.1'
+  VERSION = '0.0.2'
 end

data/spec/unit/parser_spec.rb

@@ -32,11 +32,22 @@ describe JapaneseNames::Parser do
       end
     end
 
-    [['XXX','XXX','XXX', 'XXX']].each do |kanji_fam, kanji_giv, kana_fam, kana_giv|
+    [['XXX','XXX','XXX','XXX']].each do |kanji_fam, kanji_giv, kana_fam, kana_giv|
       it "should return nil for invalid name #{kanji_fam+kanji_giv} #{kana_fam+kana_giv}" do
         result = subject.split(kanji_fam+kanji_giv, kana_fam+kana_giv)
         result.should be_nil
       end
     end
+
+    it 'should strip leading/trailing whitespace' do
+      subject.split(' 上原望 ', ' ウエハラノゾミ ').should eq [['上原','望'],['ウエハラ','ノゾミ']]
+      subject.split_giv(' 上原望 ', ' ウエハラノゾミ ').should eq [['上原','望'],['ウエハラ','ノゾミ']]
+      subject.split_fam(' 上原望 ', ' ウエハラノゾミ ').should eq [['上原','望'],['ウエハラ','ノゾミ']]
+    end
+
+    it 'should return nil for nil input' do
+      subject.split(nil, 'ウエハラノゾミ').should be_nil
+      subject.split('上原望', nil).should be_nil
+    end
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: japanese_names
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.2
 platform: ruby
 authors:
 - Johnny Shields