ruby_pinyin 1.1.0

data/lib/ruby_pinyin/punctuation.rb

@@ -0,0 +1,46 @@
+module PinYin
+  module Punctuation
+
+    class <<self
+
+      def regexp
+        return @regexp if @regexp
+
+        escaped_punctuations = punctuations.values.map {|v| "\\#{[v].pack('H*')}"}.join
+        @regexp = Regexp.new "([#{escaped_punctuations}]+)$"
+        @regexp
+      end
+
+      def chinese_regexp
+        @chinese_regexp ||= /([\u3000-\u303F\uFF00-\uFFEF]+)/
+      end
+
+      def [](code)
+        punctuations[code]
+      end
+
+      def include?(code)
+        punctuations.has_key?(code)
+      end
+
+      def punctuations
+        return @punctuations if @punctuations
+
+        @punctuations = {}
+        src = File.expand_path('../data/Punctuations.dat', __FILE__)
+        load_from src 
+
+        @punctuations
+      end
+
+      def load_from(file)
+        File.readlines(file).map do |line|
+          from, to = line.split(/\s+/)
+          @punctuations[from] = to
+        end
+      end
+
+    end
+
+  end
+end

data/lib/ruby_pinyin/util.rb

@@ -0,0 +1,29 @@
+# -*- coding: utf-8 -*-
+
+module PinYin
+  module Util
+    extend self
+
+    ASCIIMapping = {
+      'üē' => ['ue', 1], 'üé' => ['ue', 2], 'üě' => ['ue', 3], 'üè' => ['ue', 4],
+      'ā' => ['a', 1], 'ē' => ['e', 1], 'ī' => ['i', 1], 'ō' => ['o', 1], 'ū' => ['u', 1], 'ǖ' => ['v', 1],
+      'á' => ['a', 2], 'é' => ['e', 2], 'í' => ['i', 2], 'ó' => ['o', 2], 'ú' => ['u', 2], 'ǘ' => ['v', 2],
+      'ǎ' => ['a', 3], 'ě' => ['e', 3], 'ǐ' => ['i', 3], 'ǒ' => ['o', 3], 'ǔ' => ['u', 3], 'ǚ' => ['v', 3],
+      'à' => ['a', 4], 'è' => ['e', 4], 'ì' => ['i', 4], 'ò' => ['o', 4], 'ù' => ['u', 4], 'ǜ' => ['v', 4]
+    }
+
+    def to_ascii(reading, with_tone=true)
+      ASCIIMapping.each do |char, (ascii, tone)|
+        if reading.include? char
+          if with_tone
+            return reading.sub(char, ascii).concat(tone.to_s)
+          else
+            return reading.sub(char, ascii)
+          end
+        end
+      end
+      reading
+    end
+
+  end
+end

data/lib/ruby_pinyin/value.rb

@@ -0,0 +1,16 @@
+module PinYin
+  class Value < String
+    attr_accessor :english
+    alias :english? :english
+
+    def initialize(str, english=true)
+      super(str)
+      self.english = english
+    end
+
+    def split(*args)
+      result = super
+      result.map {|str| self.class.new(str, english)}
+    end
+  end
+end

data/lib/ruby_pinyin/version.rb

@@ -0,0 +1,3 @@
+module PinYin
+  VERSION = '1.1.0'
+end

data/ruby_pinyin.gemspec

@@ -0,0 +1,27 @@
+
+lib = File.expand_path("../lib", __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require "ruby_pinyin/version"
+
+Gem::Specification.new do |spec|
+  spec.name          = "ruby_pinyin"
+  spec.version       = PinYin::VERSION
+  spec.authors       = ["Charles Zhang"]
+  spec.email         = ["gis05zc@163.com"]
+
+  spec.summary     = "Convert Chinese characters into pinyin."
+  spec.description = "Pinyin is a romanization system (phonemic notation) of Chinese characters, this gem helps you to convert Chinese characters into pinyin form."
+  spec.homepage      = "https://github.com/chinazhangchao/ruby-pinyin"
+  spec.license = 'MIT'
+
+  spec.files         = `git ls-files -z`.split("\x0").reject do |f|
+    f.match(%r{^(test|spec|features)/})
+  end
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_runtime_dependency('rmmseg-cpp-new', ['~> 0.3.1'])
+  spec.add_development_dependency "bundler", "~> 1.16"
+  spec.add_development_dependency "rake", "~> 10.0"
+end

metadata

@@ -0,0 +1,107 @@
+--- !ruby/object:Gem::Specification
+name: ruby_pinyin
+version: !ruby/object:Gem::Version
+  version: 1.1.0
+platform: ruby
+authors:
+- Charles Zhang
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2017-11-11 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rmmseg-cpp-new
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.3.1
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.3.1
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.16'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.16'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+description: Pinyin is a romanization system (phonemic notation) of Chinese characters,
+  this gem helps you to convert Chinese characters into pinyin form.
+email:
+- gis05zc@163.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- Gemfile
+- Gemfile.lock
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- lib/ruby_pinyin.rb
+- lib/ruby_pinyin/backend.rb
+- lib/ruby_pinyin/backend/mmseg.rb
+- lib/ruby_pinyin/backend/simple.rb
+- lib/ruby_pinyin/data/Mandarin.dat
+- lib/ruby_pinyin/data/Punctuations.dat
+- lib/ruby_pinyin/data/words.dat
+- lib/ruby_pinyin/data/words.dic
+- lib/ruby_pinyin/punctuation.rb
+- lib/ruby_pinyin/util.rb
+- lib/ruby_pinyin/value.rb
+- lib/ruby_pinyin/version.rb
+- ruby_pinyin.gemspec
+homepage: https://github.com/chinazhangchao/ruby-pinyin
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.6.13
+signing_key: 
+specification_version: 4
+summary: Convert Chinese characters into pinyin.
+test_files: []