hanzi_to_pinyin 0.6.0 → 0.6.1

data/README.rdoc

@@ -4,9 +4,9 @@ translate chinese to pinyin , fetch first letter OR full pinyin
 
 == Install
 
-rails3 
+rails3
 
-  $ gem 'hanzi_to_pinyin' , '0.5.0'
+  $ gem 'hanzi_to_pinyin' , '0.6.0' , require: 'hanzi_to_pinyin'
 or latest develop version
   $ gem 'hanzi_to_pinyin' , git: 'git://github.com/wxianfeng/hanzi_to_pinyin.git'
 or freeze ref version
@@ -26,9 +26,13 @@ or freeze ref version
   $ HanziToPinyin.hanzi_2_py("我们") => "wo;men"
   $ HanziToPinyin.hanzi_2_py("查理Smith") => "cha,zha;li"
   $ HanziToPinyin.hanzi_2_py("测试1") => "ce;shi;1"
+  $ HanziToPinyin.hanzi_2_py("测_试") => "ce;_;shi"
 
-  $ HanziToPinyin.is_number?("1") => true
-  $ HanziToPinyin.is_number?("a") => false
+  $ HanziToPinyin.is_number?("1".ord) => true
+  $ HanziToPinyin.is_number?("a".ord) => false
+
+  $ HanziToPinyin.is_underline?("_".ord).should be_true
+  $ HanziToPinyin.is_underline?("豆豆").should be_false
 
 == Test
   $ rake spec

data/VERSION

@@ -1 +1 @@
-0.6.0
+0.6.1

data/lib/hanzi_to_pinyin.rb

@@ -14,6 +14,9 @@ class HanziToPinyin
   @@number_unicode_start = 48
   @@number_unicode_end = 57
   
+  # 下划线(10进制)
+  @@underline = 95
+  
   # 汉字 unicode 编码(16进制)
   @@unicode = YAML.load(IO.read File.expand_path("../data/unicode_to_pinyin.yml",__FILE__))
   @@py = ::JSON.parse(IO.read File.expand_path("../data/hz2py.json",__FILE__))
@@ -41,16 +44,16 @@ class HanziToPinyin
   end
   
   ##
-  # 只处理汉字和数字 多音字,分隔 字字之间;分隔
-  # 查理Smith => "cha,zha;li"
-  # 郭轶 => "guo;yi,die"
-  # 我们 => "wo;men"
-  # 宗志强 => "zong;zhi;qiang,jiang"
+  # 只处理汉字和数字和_    多音字,分隔 字字之间;分隔
+  #   查理Smith => "cha,zha;li"
+  #   郭轶 => "guo;yi,die"
+  #   我们 => "wo;men"
+  #   宗志强 => "zong;zhi;qiang,jiang"
   def self.hanzi_2_py(hanzi)
     hanzi = hanzi.force_encoding("utf-8")
     str = ''
     hanzi.each_char do |hz|
-      if is_number?(hz.ord)
+      if is_number?(hz.ord) or is_underline?(hz.ord)
         if str.length == 0
           str << hz.chr
         else
@@ -98,5 +101,9 @@ class HanziToPinyin
   def self.is_number?(number_codepoint)
     number_codepoint >= @@number_unicode_start && number_codepoint <= @@number_unicode_end
   end
+  
+  def self.is_underline?(underline_codepoint)
+    underline_codepoint == @@underline
+  end
     
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: hanzi_to_pinyin
 version: !ruby/object:Gem::Version
-  version: 0.6.0
+  version: 0.6.1
   prerelease: 
 platform: ruby
 authors:
@@ -9,12 +9,12 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-02-16 00:00:00.000000000 +08:00
+date: 2012-02-23 00:00:00.000000000 +08:00
 default_executable: 
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &86066550 !ruby/object:Gem::Requirement
+  requirement: &75722920 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -22,7 +22,7 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *86066550
+  version_requirements: *75722920
 description: chinese hanzi to pinyin , fetch first letter OR full pinyin, written
   in Ruby.
 email:
@@ -55,7 +55,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: 26390223
+      hash: 801955645
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements: