zhongwen_tools 0.16.2 → 0.16.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 671b1ec8f32959e98a77ed22cff5466f84af34f5
-  data.tar.gz: eab846d3538ccb154a895230c84b5271008fc45e
+  metadata.gz: 74821104cd7fb3bed07317f74db0e25c28055e52
+  data.tar.gz: 41d79cb06718ae207fafd2e8272c761b47d4c508
 SHA512:
-  metadata.gz: 3b439c6ec28a74108e367b1284bb0be78772aca3d1b2fd1b883e7116b096ec4b1595667068e31303ca500910a3db4b66e5918d5dce0c7e23223b83ec3be111ab
-  data.tar.gz: c7658081fecff250253d23915b1235c3caa6b88a47bdaa3c4a2f0983be819e1cfce0503443898529cd8c6ddc76012f065f1fcf6c08bbbc549268163b51b53216
+  metadata.gz: 3ed0f32087518bfc195af48a873f668e0b1b3ca0b4740b0151855d6d39363aca5ab58af10a1bc5dc9cecd67a222ee39adec42cd3c4e2edacb527fb969361734e
+  data.tar.gz: 4b8eb4a1ae1a2354195fc93714218d55ba9e29517e3001c759d1c6e25c3dad2a7fb1119b3a73ff1ee5066df71ab52942281481be2a0249a9e0e6027bff8d0b15

data/README.md

@@ -51,7 +51,7 @@ You can monkey patch the String class.
     'hello'.halfwidth?  #=> false
 
     'ｈeｌｌｏ'.fullwidth?  #=> true
-    
+
     'ｈeｌｌｏ'.to_halfwidth? #=> 'hello'
 
     '\u4e2d\u6587'.from_codepoint #=> '中文'
@@ -87,9 +87,9 @@ You can monkey patch the String class.
     'nǐ hǎo'.to_mps2 #=> 'ni3 hau3'
 
     'nǐ hǎo'.romanization? :py
-    
+
     'nǐ hǎo'.py? #=> true
-  
+
     'nǐ hǎo'.pyn? # false
 
     'nǐ hǎo'.bpmf? # false

data/lib/zhongwen_tools/regex.rb

@@ -62,7 +62,7 @@ module ZhongwenTools
     end
 
     def self.zh_number_multiple
-      /[拾十百佰千仟仟万萬亿億]/
+      /[拾十百佰千仟万萬亿億]/
     end
 
     # Public: A Regex for bopomofo, a.k.a. Zhuyin Fuhao 注音符号.
@@ -100,7 +100,7 @@ module ZhongwenTools
     end
 
     def self.py_tones
-      py_tones = {
+      {
         'a' => '[āáǎàa]',
         'e' => '[ēéěèe]',
         'i' => '[īíǐìi]',
@@ -109,5 +109,9 @@ module ZhongwenTools
         'v' => '[ǖǘǚǜü]'
       }
     end
+
+    def self.only_tones
+      /([āáǎàēéěèīíǐìōóǒòūúǔùǖǘǚǜ])/
+    end
   end
 end

data/lib/zhongwen_tools/romanization/pinyin.rb

@@ -48,6 +48,8 @@ module ZhongwenTools
 
         results = words.map do |word|
           word, is_capitalized = normalize_pinyin(word)
+          # NOTE: Special Case "fǎnguāng" should be "fǎn" + "guāng"
+          word = word.gsub('ngu', 'n-gu')
           result = word.split(/['\-]/).flatten.map do |x|
             find_py(x)
           end
@@ -67,10 +69,15 @@ module ZhongwenTools
       #
       # Returns Boolean.
       def self.py?(str)
-        # NOTE: py regex does not include capitals with tones.
-        #ZhongwenTools::Caps.downcase(str).gsub(ZhongwenTools::Regex.punc,'').gsub(Regex.py, '').gsub(/[\s\-]/,'').strip == ''
-        regex = /(#{ ZhongwenTools::Regex.punc }|#{ ZhongwenTools::Regex.py }|[\s\-])/
+        if str[ZhongwenTools::Regex.only_tones].nil? && str[/[1-5]/].nil?
+          pyn?(str)
+        else
+          # NOTE: py regex does not include capitals with tones.
+          # NOTE: Special Case "fǎnguāng" should be "fǎn" + "guāng"
+          regex = /(#{ ZhongwenTools::Regex.punc }|#{ ZhongwenTools::Regex.py }|[\s\-])/
+          str = str.gsub('ngu', 'n-gu')
           ZhongwenTools::Caps.downcase(str).gsub(regex, '').strip == ''
+        end
       end
 
       # Public: checks if a string is pinyin.
@@ -126,7 +133,6 @@ module ZhongwenTools
 
       def self.find_py(str)
         str.scan(ZhongwenTools::Regex.py).map{ |x| (x - [nil])[0] }
-
       end
 
       def self.recapitalize(obj, capitalized)
@@ -177,7 +183,7 @@ module ZhongwenTools
             pyn = pyn.sub(/(#{replacements.join('.*')}.*)#{match}/){ $1 + replace }
           else
             pyn = pyn.sub(/#{match}/){ "#{$1}#{replace}"}
-            end
+          end
           replacements << replace
         end
 

data/lib/zhongwen_tools/version.rb

@@ -1,3 +1,3 @@
 module ZhongwenTools
-  VERSION = '0.16.2'
+  VERSION = '0.16.4'
 end

data/test/test_pinyin.rb

@@ -14,6 +14,8 @@ class TestPinyin < Minitest::Test
     @split_words.each do |w|
       assert_equal w[:split_py], ZhongwenTools::Romanization::Pinyin.split_py(w[:py])
     end
+
+    assert_equal ['fǎn', 'guāng', 'jìng'], ZhongwenTools::Romanization::Pinyin.split_py('fǎnguāngjìng')
   end
 
   def test_py?
@@ -21,6 +23,14 @@ class TestPinyin < Minitest::Test
       assert ZhongwenTools::Romanization::Pinyin.py?(w[:py]), w.inspect
       refute ZhongwenTools::Romanization::Pinyin.py?(w[:pyn]), w.inspect
     end
+
+    assert  ZhongwenTools::Romanization::Pinyin.py? 'fǎnguāngjìng'
+
+    english_words = %w(cyan moose cling touch)
+
+    english_words.each do |w|
+      refute ZhongwenTools::Romanization::Pinyin.py? w
+    end
   end
 
   def test_pyn?
@@ -58,13 +68,13 @@ class TestPinyin < Minitest::Test
 
 
     @words = [
-      {:pyn => 'A1la1bo2', :py => 'Ālābó'},
-      { :pyn => 'ni3 hao3', :py => 'nǐ hǎo' },
-      { :pyn => 'Zhong1guo2', :py => 'Zhōngguó' },
-      { :pyn => 'chui1 niu3', :py => "chuī niǔ" },
-      { :pyn => 'Mao2 Ze2dong1', :py => 'Máo Zédōng' },
+      { pyn: 'A1la1bo2', py: 'Ālābó'},
+      { pyn: 'ni3 hao3', py: 'nǐ hǎo' },
+      { pyn: 'Zhong1guo2', py: 'Zhōngguó' },
+      { pyn: 'chui1 niu3', py: "chuī niǔ" },
+      { pyn: 'Mao2 Ze2dong1', py: 'Máo Zédōng' }
     ]
 
-    @r =  { :pyn => 'r5', :py => 'r' }
+    @r =  { pyn: 'r5', py: 'r' }
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: zhongwen_tools
 version: !ruby/object:Gem::Version
-  version: 0.16.2
+  version: 0.16.4
 platform: ruby
 authors:
 - Steven Daniels
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-09-15 00:00:00.000000000 Z
+date: 2014-11-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake