ruby-pinyin 0.2.0 → 0.2.1

data/README.markdown

@@ -6,8 +6,13 @@
 * 能够显示数字或者UNICODE音调(eg: 'cao1', 'cāo')
 * 丰富的API
 * 支持中英文标点混合字符串
+* 中文标点转为英文标点
 * 支持自定义读音
 
+## Installation
+
+        gem install ruby-pinyin
+
 ## Examples
 
         # encoding: utf-8
@@ -33,8 +38,8 @@
         PinYin.abbr('感谢party感谢guo jia')
 
         # return 'gan xie party, gan xie guo jia!'
-        # PinYin.sentence保留标点符号
-        PinYin.sentence('感谢party, 感谢guo家!')
+        # PinYin.sentence保留标点符号, 同时用对应英文标点代替中文标点
+        PinYin.sentence('感谢party， 感谢guo家！')
 
         # override readings with your own data file
         PinYin.override_files = [File.expand_path('../my.dat', __FILE__)]

data/lib/ruby-pinyin.rb

@@ -23,6 +23,16 @@ module PinYin
       @codes
     end
 
+    def punctuations
+      return @punctuations if @punctuations
+
+      @punctuations = {}
+      src = File.expand_path('../ruby-pinyin/Punctuations.dat', __FILE__)
+      load_punctuations_from(src)
+
+      @punctuations
+    end
+
     def of_string(str, tone=nil, include_punctuations=false)
       res = []
       return res unless str && !str.empty?
@@ -38,6 +48,7 @@ module PinYin
           if val =~ /^[_0-9a-zA-Z\s]*$/ # 复原，去除特殊字符,如全角符号等。
             (res.last && res.last.english? ? res.last : res) << Value.new(val, true) # 如果上一个字符也是非中文则与之合并
           elsif include_punctuations
+            val = [punctuations[code]].pack('H*') if punctuations.has_key?(code)
             (res.last ? res.last : res) << Value.new(val, false)
           end
         end
@@ -74,6 +85,13 @@ module PinYin
       end
     end
 
+    def load_punctuations_from(file)
+      File.readlines(file).map do |line|
+        from, to = line.split(/\s+/)
+        @punctuations[from] = to
+      end
+    end
+
     def format(readings, tone)
       case tone
       when :unicode

data/lib/ruby-pinyin/Punctuations.dat

@@ -0,0 +1,9 @@
+FF0C 2C
+3002 2E
+FF01 21
+FF1F 3F
+FF1A 3A
+201C 22
+201D 22
+2018 27
+2019 27

data/lib/ruby-pinyin/version.rb

@@ -1,3 +1,3 @@
 module PinYin
-  VERSION = '0.2.0'
+  VERSION = '0.2.1'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: ruby-pinyin
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.2.1
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-05-05 00:00:00.000000000 Z
+date: 2013-05-18 00:00:00.000000000 Z
 dependencies: []
 description: Pinyin is a romanization system (phonemic notation) of Chinese characters,
   this gem helps you to convert Chinese characters into pinyin form.
@@ -23,6 +23,7 @@ files:
 - lib/ruby-pinyin/version.rb
 - lib/ruby-pinyin/value.rb
 - lib/ruby-pinyin/Mandarin.dat
+- lib/ruby-pinyin/Punctuations.dat
 - MIT-LICENSE
 - README.markdown
 homepage: https://github.com/janx/ruby-pinyin