string_to_pinyin 1.0.0

data/lib/string_to_pinyin.rb

@@ -0,0 +1,19 @@
+# encoding: utf-8
+class String
+
+  def to_pinyin
+    idx_file_path = File.expand_path('../../data/idx99-tone.txt',__FILE__)
+    result = ""
+    self.scan(/./) do |char|
+      match = %x[grep -m1 '^#{char}' #{idx_file_path}]
+      if match.empty?
+        result = result + char
+      else
+        pinyin =  match.gsub("\n","").split("\t")[1]
+        result = result + pinyin + " "
+      end
+    end
+    return result.rstrip
+  end
+      
+end

data/spec/spec.opts

@@ -0,0 +1,5 @@
+--color
+--format progress
+--loadby mtime
+--reverse
+

data/spec/spec_helper.rb

@@ -0,0 +1,10 @@
+# encoding: utf-8
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+require 'string_to_pinyin'
+require 'spec'
+require 'spec/autorun'
+
+Spec::Runner.configure do |config|
+  
+end

data/spec/string_to_pinyin_spec.rb

@@ -0,0 +1,27 @@
+# encoding: utf-8
+require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
+
+describe "StringToPinyin" do
+  before :each do
+    @single_char = "名"
+    @multiple_chars = "中华人民共和国"
+    @nil_char = "a"
+    @punctuated = "你好! 你是中国人吗? <- that was mandarin"
+  end
+  
+  it "should return pinyin for a single character if found" do
+    @single_char.to_pinyin.should == 'míng'
+  end
+  
+  it "should return pinyin with spaces in between for multiple characters if found" do
+    @multiple_chars.to_pinyin.should == 'zhōng huá rén mín gòng hé guó'
+  end
+  
+  it "should return a character if its not found in the index" do
+    @nil_char.to_pinyin.should == 'a'
+  end
+
+  it "should return 'non-simplified chinese characters' as they are" do
+    @punctuated.to_pinyin.should == 'nĭ hăo ! nĭ shì zhōng guó rén ma ? <- that was mandarin'
+  end
+end

metadata

@@ -0,0 +1,98 @@
+--- !ruby/object:Gem::Specification 
+name: string_to_pinyin
+version: !ruby/object:Gem::Version 
+  hash: 23
+  prerelease: false
+  segments: 
+  - 1
+  - 0
+  - 0
+  version: 1.0.0
+platform: ruby
+authors: 
+- Toritaba
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2010-06-30 00:00:00 +05:30
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: rspec
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 13
+        segments: 
+        - 1
+        - 2
+        - 9
+        version: 1.2.9
+  type: :development
+  version_requirements: *id001
+description: Adds a 'to_pinyin' method to Ruby's String class to convert Simplified Chinese characters to Hanyu Pinyin
+email: toritaba@gmail.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- LICENSE
+- README
+files: 
+- .gitignore
+- CHANGELOG
+- CREDITS
+- LICENSE
+- README
+- Rakefile
+- VERSION
+- data/idx99-tone.txt
+- lib/string_to_pinyin.rb
+- pkg/string_to_pinyin-0.1.0.gem
+- pkg/string_to_pinyin-0.1.1.gem
+- pkg/string_to_pinyin-0.2.0.gem
+- spec/spec.opts
+- spec/spec_helper.rb
+- spec/string_to_pinyin_spec.rb
+has_rdoc: true
+homepage: http://github.com/toritaba/string_to_pinyin
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --charset=UTF-8
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.7
+signing_key: 
+specification_version: 3
+summary: Converts Simplified Chinese characters to pinyin
+test_files: 
+- spec/string_to_pinyin_spec.rb
+- spec/spec_helper.rb