chinese_pinyin 0.5.0 → 0.6.0

data/lib/chinese_pinyin.rb

@@ -6,13 +6,19 @@ require 'chinese_pinyin/version'
 class Pinyin
   class <<self
     attr_accessor :table
+    attr_accessor :ruby2
 
     def init_table
       return if @table
-      @table = {}
-      open(File.dirname(__FILE__) + '/../data/Mandarin.dat') do |file|
+
+      # Ruby 2.0以后默认即为UTF-8编码，使用新的码表以提升效率
+      @ruby2  = !!(RUBY_VERSION =~ /^2/)
+      datfile = @ruby2 ? 'pinyin-utf8.dat' : 'Mandarin.dat'
+      @table  = {}
+
+      File.open(File.dirname(__FILE__) + "/../data/#{datfile}") do |file|
         while line = file.gets
-          key, value = line.split(' ', 2)
+          key, value  = line.split(' ', 2)
           @table[key] = value
         end
       end
@@ -20,11 +26,13 @@ class Pinyin
 
     def init_word_table
       return if @words_table
+
       @words_table = {}
+
       if ENV["WORDS_FILE"]
-        open(ENV["WORDS_FILE"]) do |file|
+        File.open(ENV["WORDS_FILE"]) do |file|
           while line = file.gets
-            key, value = line.sub("\n", "").split('|', 2)
+            key, value        = line.sub("\n", "").split('|', 2)
             @words_table[key] = value
           end
         end
@@ -32,24 +40,41 @@ class Pinyin
     end
 
     def translate(chars, options={})
-      splitter = options[:splitter] || ' '
-      tone = options[:tone] || false
+      splitter = options.fetch(:splitter, ' ')
+      tone     = options.fetch(:tone, false)
+      camel    = options.fetch(:camelcase, false)
 
       init_word_table
-      return @words_table[chars].gsub(' ', splitter) if @words_table[chars]
+      results = @words_table[chars]
+      if results
+        results = results.split
+        results.map!(&:downcase)
+        results.map!(&:capitalize) if camel
+        results.map! { |x| (48..57).include?(x[-1].ord) ? x.chop! : x } unless tone
+
+        return results.join(splitter)
+      end
 
       init_table
-      results = []
+      results    = []
       is_english = false
+
       chars.scan(/./).each do |char|
-        key = sprintf("%X", char.unpack("U").first)
+        key = @ruby2 ? char : sprintf("%X", char.unpack("U").first)
+
         if @table[key]
           results << splitter if is_english
-          pinyin = @table[key].chomp.split(' ', 2)[0].downcase
+
+          is_english = false
+          pinyin     = @table[key].chomp.split(' ', 2)[0]
+
+          pinyin.downcase! unless @ruby2
           pinyin.chop! unless tone
+          pinyin.capitalize! if camel
+
           results << pinyin
           results << splitter
-          is_english = false
+
         else
           results << char
           is_english = true

data/lib/chinese_pinyin/version.rb

@@ -1,4 +1,4 @@
 # encoding: utf-8
 module ChinesePinyin
-  VERSION = "0.5.0"
+  VERSION = "0.6.0"
 end

data/test/Words.dat

@@ -1 +1,2 @@
 广州|guang zhou
+上海|ShANg4 hAi3

data/test/chinese_pinyin_test.rb

@@ -7,16 +7,31 @@ class PinyinTest < Test::Unit::TestCase
   def test_t
     assert_equal("zhong guo", Pinyin.t('中国'))
     assert_equal("zhong guo english ri", Pinyin.t('中国english日'))
+    assert_equal("shang hai very good o ye", Pinyin.t('上海very good哦耶'))
   end
 
   def test_t_with_splitter
     assert_equal("zhong-guo", Pinyin.t('中国', splitter: '-'))
     assert_equal("huangzhimin", Pinyin.t('黄志敏', splitter: ''))
     assert_equal("guang-zhou", Pinyin.t('广州', splitter: '-'))
+    assert_equal("shang-hai", Pinyin.t('上海', splitter: '-'))
   end
 
   def test_t_with_tone
     assert_equal("zhong1 guo2", Pinyin.t('中国', tone: true))
     assert_equal("huang2 zhi4 min3", Pinyin.t('黄志敏', tone: true))
+    assert_equal("shang4 hai3", Pinyin.t('上海', tone: true))
+  end
+
+  def test_t_with_camelcase
+    assert_equal("Zhong Guo", Pinyin.t('中国', camelcase: true))
+    assert_equal("Huang Zhi Min", Pinyin.t('黄志敏', camelcase: true))
+    assert_equal("Zhong1 Guo2", Pinyin.t('中国', camelcase: true, tone: true))
+    assert_equal("Huang2 Zhi4 Min3", Pinyin.t('黄志敏', camelcase: true, tone: true))
+    assert_equal("Zhong-Guo", Pinyin.t('中国', camelcase: true, splitter: '-'))
+    assert_equal("HuangZhiMin", Pinyin.t('黄志敏', camelcase: true, splitter: ''))
+    assert_equal("Guang-Zhou", Pinyin.t('广州', camelcase: true, splitter: '-'))
+    assert_equal("Shang-Hai", Pinyin.t('上海', camelcase: true, splitter: '-'))
+    assert_equal("Shang4-Hai3", Pinyin.t('上海', camelcase: true, tone:true, splitter: '-'))
   end
 end

metadata

@@ -1,18 +1,20 @@
 --- !ruby/object:Gem::Specification
 name: chinese_pinyin
 version: !ruby/object:Gem::Version
-  version: 0.5.0
+  version: 0.6.0
 platform: ruby
 authors:
 - Richard Huang
+- Hong, Liang
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-06-27 00:00:00.000000000 Z
+date: 2013-09-04 00:00:00.000000000 Z
 dependencies: []
 description: translate chinese hanzi to pinyin.
 email:
 - flyerhzm@gmail.com
+- hongliang@bamajia.com
 executables: []
 extensions: []
 extra_rdoc_files: []
@@ -26,6 +28,7 @@ files:
 - Rakefile
 - chinese_pinyin.gemspec
 - data/Mandarin.dat
+- data/pinyin-utf8.dat
 - lib/chinese_pinyin.rb
 - lib/chinese_pinyin/version.rb
 - test/Words.dat
@@ -50,7 +53,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: 1.3.6
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.0.3
+rubygems_version: 2.0.5
 signing_key: 
 specification_version: 4
 summary: translate chinese hanzi to pinyin.