chinese_pinyin 0.3.0 → 0.4.0

data/README.md

@@ -1,21 +1,40 @@
-# ChinesePinyin
+ChinesePinyin
+=============
 
 Translate chinese hanzi to pinyin.
 
-The dict is borrowed from http://github.com/fayland/perl-lingua-han/tree/master/Lingua-Han-PinYin/
+The dict is borrowed from <http://github.com/fayland/perl-lingua-han/tree/master/Lingua-Han-PinYin/>
 
-## Install
+Install
+-------
 
-<pre><code>sudo gem install chinese_pinyin</code></pre>
+    sudo gem install chinese_pinyin
 
-## Usage
+Usage
+-----
 
-<pre><code>
-require 'rubygems'
-require 'chinese_pinyin'
+    require 'rubygems'
+    require 'chinese_pinyin'
 
-Pinyin.t('中国')  => "zhong guo"
-Pinyin.t('中国', '-') => "zhong-guo"
-Pinyin.t('中国', '') => "zhongguo"
-Pinyin.t('你好world') => "ni hao world"
-</code></pre>
+    Pinyin.t('中国')  => "zhong guo"
+    Pinyin.t('中国', '-') => "zhong-guo"
+    Pinyin.t('中国', '') => "zhongguo"
+    Pinyin.t('你好world') => "ni hao world"
+
+Polyphone Issue
+---------------
+
+use Words.dat to override default behavior.
+
+by default
+
+    Pinyin.t('广州') => "yan zhou"
+
+add file Words.dat
+
+    广州|guang zhou
+
+set ENV['WORDS_FILE'] for Words.dat
+
+    ENV['WORDS_FILE'] = "Words.dat path"
+    Pinyin.t('广州') => "guang zhou"

data/VERSION

@@ -1 +1 @@
-0.3.0
+0.4.0

data/chinese_pinyin.gemspec

@@ -1,15 +1,15 @@
 # Generated by jeweler
 # DO NOT EDIT THIS FILE DIRECTLY
-# Instead, edit Jeweler::Tasks in Rakefile, and run the gemspec command
+# Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
 # -*- encoding: utf-8 -*-
 
 Gem::Specification.new do |s|
   s.name = %q{chinese_pinyin}
-  s.version = "0.3.0"
+  s.version = "0.4.0"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Richard Huang"]
-  s.date = %q{2011-08-27}
+  s.date = %q{2011-10-08}
   s.description = %q{translate chinese hanzi to pinyin.}
   s.email = %q{flyerhzm@gmail.com}
   s.extra_rdoc_files = [
@@ -17,23 +17,19 @@ Gem::Specification.new do |s|
   ]
   s.files = [
     "README.md",
-     "Rakefile",
-     "VERSION",
-     "chinese_pinyin.gemspec",
-     "data/Mandarin.dat",
-     "lib/chinese_pinyin.rb",
-     "test/chinese_pinyin_test.rb",
-     "test/test_helper.rb"
+    "Rakefile",
+    "VERSION",
+    "chinese_pinyin.gemspec",
+    "data/Mandarin.dat",
+    "lib/chinese_pinyin.rb",
+    "test/Words.dat",
+    "test/chinese_pinyin_test.rb",
+    "test/test_helper.rb"
   ]
   s.homepage = %q{http://github.com/flyerhzm/chinese_pinyin}
-  s.rdoc_options = ["--charset=UTF-8"]
   s.require_paths = ["lib"]
   s.rubygems_version = %q{1.6.2}
   s.summary = %q{translate chinese hanzi to pinyin.}
-  s.test_files = [
-    "test/chinese_pinyin_test.rb",
-     "test/test_helper.rb"
-  ]
 
   if s.respond_to? :specification_version then
     s.specification_version = 3

data/lib/chinese_pinyin.rb

@@ -2,7 +2,7 @@
 $KCODE = 'u' if RUBY_VERSION !~ /1\.9/
 
 class Pinyin
-  
+
   class <<self
     attr_accessor :table
 
@@ -17,7 +17,23 @@ class Pinyin
       end
     end
 
+    def init_word_table
+      return if @words_table
+      @words_table = {}
+      if ENV["WORDS_FILE"]
+        open(ENV["WORDS_FILE"]) do |file|
+          while line = file.gets
+            key, value = line.sub("\n", "").split('|', 2)
+            @words_table[key] = value
+          end
+        end
+      end
+    end
+
     def translate(chars, splitter = ' ')
+      init_word_table
+      return @words_table[chars].gsub(' ', splitter) if @words_table[chars]
+
       init_table
       results = []
       is_english = false

data/test/Words.dat

@@ -0,0 +1 @@
+广州|guang zhou

data/test/chinese_pinyin_test.rb

@@ -1,6 +1,8 @@
 # -*- encoding : utf-8 -*-
 require 'test_helper'
 
+ENV["WORDS_FILE"] = File.dirname(__FILE__) + '/Words.dat'
+
 class PinyinTest < Test::Unit::TestCase
   def test_t
     assert_equal("zhong guo", Pinyin.t('中国'))
@@ -9,5 +11,7 @@ class PinyinTest < Test::Unit::TestCase
     assert_equal("huangzhimin", Pinyin.t('黄志敏', ''))
 
     assert_equal("zhong guo english ri", Pinyin.t('中国english日'))
+
+    assert_equal("guang-zhou", Pinyin.t('广州', '-'))
   end
 end

metadata

@@ -2,7 +2,7 @@
 name: chinese_pinyin
 version: !ruby/object:Gem::Version 
   prerelease: 
-  version: 0.3.0
+  version: 0.4.0
 platform: ruby
 authors: 
 - Richard Huang
@@ -10,7 +10,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-08-27 00:00:00 +08:00
+date: 2011-10-08 00:00:00 +08:00
 default_executable: 
 dependencies: []
 
@@ -29,6 +29,7 @@ files:
 - chinese_pinyin.gemspec
 - data/Mandarin.dat
 - lib/chinese_pinyin.rb
+- test/Words.dat
 - test/chinese_pinyin_test.rb
 - test/test_helper.rb
 has_rdoc: true
@@ -36,8 +37,8 @@ homepage: http://github.com/flyerhzm/chinese_pinyin
 licenses: []
 
 post_install_message: 
-rdoc_options: 
-- --charset=UTF-8
+rdoc_options: []
+
 require_paths: 
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement 
@@ -59,6 +60,5 @@ rubygems_version: 1.6.2
 signing_key: 
 specification_version: 3
 summary: translate chinese hanzi to pinyin.
-test_files: 
-- test/chinese_pinyin_test.rb
-- test/test_helper.rb
+test_files: []
+