chinese_pinyin 0.7.0 → 1.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 536820144ef1284e973430e684d7511a5f4a21b5
-  data.tar.gz: 235adb7c959a9c0a01e3d2234ac1abf75fefc79a
+SHA256:
+  metadata.gz: 23e4d70b5131cb483c5a9a6a542b1310ad4cad4535e8d295ff58ba9338f2b930
+  data.tar.gz: 1224699549ee0d9d644e1f96d084a3c17c7754f9236d2a21311a152fafd73b52
 SHA512:
-  metadata.gz: fcf06b8a4f831aac76d9ecd772b972f05b855e70fab14fca2d40aa5f6504fdd4045a56bc5a84dc22e1bb0cf857d72b6e6f0ce8133f37d95dae78f2f05e360330
-  data.tar.gz: 526585ebbd8b4ecc987f31d5c591cbc8352708df9af9601f1a01c8ae8bb22f06da2da73e6017f2fbbd6f8b71e747009e16f2a6c88b0c0d215fe61c4222268b95
+  metadata.gz: 4d913acf6b8b162685957081afc5ccc6a47337e1a5481bb347a27ae8748c16f87f56c367c0a064fe1b09246d288c7680064bb1f4673dcebce669f64e3c9b458d
+  data.tar.gz: 5974408e11538bc96644ef3b8f7b41c9b5a381719bd495347217eb5165a8771dc34d7d94c810bb0543b66aaa6a79c2d64aa268845187dad167244836cf032950

data/.github/workflows/chinese_pinyin.yml

@@ -0,0 +1,26 @@
+name: Chinese Pinyin
+
+on:
+  pull_request:
+    branches:
+      - 'master'
+  
+  push:
+    branches:
+      - 'ruby3-support'
+      - 'master'
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        ruby: ['2.1', '2.5', '2.6', '2.7', '3.0']
+    steps:
+    - uses: actions/checkout@v1
+    - uses: ruby/setup-ruby@v1
+      with:
+        ruby-version: ${{ matrix.ruby }}
+    - name: Build and test with Rake
+      run: |
+        rake test

data/CHANGELOG.md

@@ -0,0 +1,18 @@
+# Next Release
+
+## 1.1.0 (04/19/2021)
+
+* support ruby 3
+
+## 1.0.2 (08/19/2019)
+
+* add 嗯 to pinyin-utf8.dat
+
+## 1.0.1
+
+* force utf8
+
+## 1.0.0 (06/23/2015)
+
+* add executable cmd ch2py
+* fix tone marks

data/README.md

@@ -1,42 +1,79 @@
-ChinesePinyin
-=============
+# ChinesePinyin
+
+[![Chinese Pinyin](https://github.com/flyerhzm/chinese_pinyin/actions/workflows/chinese_pinyin.yml/badge.svg)](https://github.com/flyerhzm/chinese_pinyin/actions/workflows/chinese_pinyin.yml)
 
 Translate chinese hanzi to pinyin.
 
 The dict is borrowed from <http://github.com/fayland/perl-lingua-han/tree/master/Lingua-Han-PinYin/>
 
-Install
--------
+## Install
+
+```
+gem install chinese_pinyin
+```
+
+or add in Gemfile.
+
+```
+gem 'chinese_pinyin'
+```
+
+## Usage
+
+By CLI
+
+
+```
+$ ch2py -h
+Usage: ch2py [opts]
+    -c, --camelcase                  Camelcase of each word
+    -i, --stdin                      Read from stdard input
+    -t, --tone                       Show tone at end of word
+    -m, --tonemarks                  Show tone at top of letter, this
+would cover -t option
+    -s, --splitter <splitter>        Splitter of each word, use a space
+by default
+    -v, --version                    Show version
+    -h, --help                       Show this help
 
-    sudo gem install chinese_pinyin
+$ ch2py 中文
+zhong wen
+```
 
-Usage
------
+By code
 
-    require 'rubygems'
-    require 'chinese_pinyin'
+```
+require 'chinese_pinyin'
 
-    Pinyin.t('中国')  => "zhong guo"
-    Pinyin.t('你好world') => "ni hao world"
-    Pinyin.t('中国', splitter: '-') => "zhong-guo"
-    Pinyin.t('中国', splitter: '') => "zhongguo"
-    Pinyin.t('中国', tone: true) => "zhong1 guo2"
-    Pinyin.t('中国', tonemarks: true) => "zhōng guó"
+Pinyin.t('中国')  => "zhong guo"
+Pinyin.t('你好world') => "ni hao world"
+Pinyin.t('中国', splitter: '-') => "zhong-guo"
+Pinyin.t('中国', splitter: '') => "zhongguo"
+Pinyin.t('中国', tone: true) => "zhong1 guo2"
+Pinyin.t('中国', tonemarks: true) => "zhōng guó"
+Pinyin.t('北京') { |letters| letters[0].upcase } => 'BJ'
+Pinyin.t('北京') { |letters, i| letters[0].upcase if i == 0 } => 'B'
+```
 
-Polyphone Issue
----------------
+## Polyphone Issue
 
 use Words.dat to override default behavior.
 
 by default
 
-    Pinyin.t('广州') => "yan zhou"
+```
+Pinyin.t('广州') => "yan zhou"
+```
 
 add file Words.dat
 
-    广州|guang3 zhou1
+```
+广州|guang3 zhou1
+```
 
-set ENV['WORDS_FILE'] for Words.dat
+set `ENV['WORDS_FILE']` for Words.dat
 
-    ENV['WORDS_FILE'] = "Words.dat path"
-    Pinyin.t('广州') => "guang zhou"
+```
+ENV['WORDS_FILE'] = "Words.dat path"
+Pinyin.t('广州') => "guang zhou"
+```

data/Rakefile

@@ -1,8 +1,6 @@
 $LOAD_PATH.unshift File.expand_path("../lib", __FILE__)
-require "bundler"
-Bundler.setup
 
-require "rake"
+require 'bundler/setup'
 require 'rake/testtask'
 require "rdoc/task"
 

data/bin/ch2py

@@ -0,0 +1,54 @@
+#!/usr/bin/env ruby
+
+require 'optparse'
+require File.expand_path('../../lib/chinese_pinyin', __FILE__)
+
+opts = {}
+
+parser = OptParse.new do |opt|
+  opt.banner = "Usage: ch2py [opts]"
+
+  opt.on('-c', '--camelcase', 'Camelcase of each word') do
+    opts[:camelcase] = true
+  end
+
+  opt.on('-i', '--stdin', 'Read from stdard input') do
+    opts[:stdin] = true
+  end
+
+  opt.on('-t', '--tone', 'Show tone at end of word') do
+    opts[:tone] = true
+  end
+
+  opt.on('-m', '--tonemarks', 'Show tone at top of letter, this would cover -t option') do
+    opts[:tonemarks] = true
+  end
+
+  opt.on('-s', '--splitter <splitter>', 'Splitter of each word, use a space by default') do |sp|
+    opts[:splitter] = sp
+  end
+
+  opt.on('-v', '--version', 'Show version') do
+    puts "ch2py: Version #{ChinesePinyin::VERSION}"
+    exit
+  end
+
+  opt.on('-h', '--help', 'Show this help') do
+    puts parser
+    exit
+  end
+end
+
+parser.parse!
+
+args = parser.default_argv
+
+if opts.fetch(:stdin, false)
+  chars = STDIN.readline
+elsif args.empty?
+  raise OptParse::MissingArgument
+else
+  chars = args.join('')
+end
+
+STDOUT.puts Pinyin.t(chars, opts)

data/chinese_pinyin.gemspec

@@ -6,6 +6,7 @@ require "chinese_pinyin/version"
 Gem::Specification.new do |s|
   s.name        = "chinese_pinyin"
   s.version     = ChinesePinyin::VERSION
+  s.license     = "MIT"
   s.platform    = Gem::Platform::RUBY
   s.authors     = ["Richard Huang", "Hong, Liang"]
   s.email       = ["flyerhzm@gmail.com", "hongliang@bamajia.com"]
@@ -18,4 +19,6 @@ Gem::Specification.new do |s|
   s.files         = `git ls-files`.split("\n")
   s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
   s.require_paths = ["lib"]
+
+  s.executables   = ["ch2py"]
 end

data/data/pinyin-utf8.dat

@@ -25357,3 +25357,4 @@
 𧵳 she2
 𧼮 tang1
 𩜇 juan3
+嗯 en1

data/lib/chinese_pinyin.rb

@@ -6,27 +6,28 @@ require 'chinese_pinyin/version'
 class Pinyin
 
   TONE_MARK = {
-    a: %w(a ā á ǎ à),
-    o: %w(o ō ó ǒ ò),
-    e: %w(e ē é ě è),
-    i: %w(i ī í ǐ ì),
-    u: %w(u ū ú ǔ ù),
-    v: %w(ü ǖ ǘ ǚ ǜ)
+    a: %w(ā á ǎ à a),
+    o: %w(ō ó ǒ ò o),
+    e: %w(ē é ě è e),
+    i: %w(ī í ǐ ì i),
+    u: %w(ū ú ǔ ù u),
+    v: %w(ǖ ǘ ǚ ǜ ü)
   }
 
   class <<self
     attr_accessor :table
-    attr_accessor :ruby2
+    attr_accessor :ruby1
 
     def init_table
       return if @table
 
       # 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'
+      @ruby1  = !!(RUBY_VERSION =~ /^1/)
+      datfile = @ruby1 ? 'Mandarin.dat' : 'pinyin-utf8.dat'
       @table  = {}
 
-      File.open(File.dirname(__FILE__) + "/../data/#{datfile}") do |file|
+      file = File.join(File.dirname(__FILE__), "../data/#{datfile}")
+      File.open(file, "r:UTF-8",) do |file|
         while line = file.gets
           key, value  = line.split(' ', 2)
           @table[key] = value
@@ -50,6 +51,7 @@ class Pinyin
     end
 
     def translate(chars, options={})
+      chars     = chars.encode("UTF-8")
       splitter  = options.fetch(:splitter, ' ')
       tonemarks = options.fetch(:tonemarks, false)
       tone      = options.fetch(:tone, false || tonemarks)
@@ -71,7 +73,7 @@ class Pinyin
       is_english = false
 
       chars.scan(/./).each do |char|
-        key = @ruby2 ? char : sprintf("%X", char.unpack("U").first)
+        key = @ruby1 ? sprintf("%X", char.unpack("U").first) : char
 
         if @table[key]
           results << splitter if is_english
@@ -79,19 +81,22 @@ class Pinyin
           is_english = false
           pinyin     = @table[key].chomp.split(' ', 2)[0]
 
-          pinyin.downcase! unless @ruby2
+          pinyin.downcase! if @ruby1
           pinyin.chop! unless tone
           pinyin.capitalize! if camel
           if tonemarks
             tone_index = pinyin[-1].to_i
             pinyin = pinyin[0...-1]
             %w(a o e i u v).each { |v|
-              break if pinyin.tr! v, TONE_MARK[v.to_sym][tone_index]
+              break if pinyin.tr! v, TONE_MARK[v.to_sym][tone_index - 1]
             }
           end
-
-          results << pinyin
-          results << splitter
+          if block_given?
+            results << (yield pinyin, results.size)
+          else
+            results << pinyin
+            results << splitter
+          end
         else
           if char =~ /[a-zA-Z0-9]/
             results << char

data/lib/chinese_pinyin/version.rb

@@ -1,4 +1,5 @@
 # encoding: utf-8
+
 module ChinesePinyin
-  VERSION = "0.7.0"
+  VERSION = "1.1.0"
 end

data/test/chinese_pinyin_test.rb

@@ -1,4 +1,5 @@
 # -*- encoding : utf-8 -*-
+
 require File.expand_path(File.join(File.dirname(__FILE__), 'test_helper'))
 
 ENV["WORDS_FILE"] = File.dirname(__FILE__) + '/Words.dat'
@@ -10,6 +11,11 @@ class PinyinTest < Test::Unit::TestCase
     assert_equal("shang hai very good o ye", Pinyin.t('上海very good哦耶'))
   end
 
+  def test_t_with_frozen_string
+    assert_equal("zhong guo", Pinyin.t('中国'.freeze))
+    assert_equal("shen zhen", Pinyin.t('深圳'.freeze))
+  end
+
   def test_t_with_splitter
     assert_equal("zhong-guo", Pinyin.t('中国', splitter: '-'))
     assert_equal("huangzhimin", Pinyin.t('黄志敏', splitter: ''))
@@ -43,4 +49,9 @@ class PinyinTest < Test::Unit::TestCase
     assert_equal('zhōng guó', Pinyin.t('中国', tonemarks: true))
     assert_equal('běi jīng', Pinyin.t('北京', tonemarks: true))
   end
+
+  def test_t_with_custom
+    assert_equal('BJ', Pinyin.t('北京') { |letters| letters[0].upcase } )
+    assert_equal('B', Pinyin.t('北京') { |letters, i| letters[0].upcase if i == 0 } )
+  end
 end

metadata

@@ -1,31 +1,33 @@
 --- !ruby/object:Gem::Specification
 name: chinese_pinyin
 version: !ruby/object:Gem::Version
-  version: 0.7.0
+  version: 1.1.0
 platform: ruby
 authors:
 - Richard Huang
 - Hong, Liang
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2015-03-10 00:00:00.000000000 Z
+date: 2021-04-18 00:00:00.000000000 Z
 dependencies: []
 description: translate chinese hanzi to pinyin.
 email:
 - flyerhzm@gmail.com
 - hongliang@bamajia.com
-executables: []
+executables:
+- ch2py
 extensions: []
 extra_rdoc_files: []
 files:
+- ".github/workflows/chinese_pinyin.yml"
 - ".gitignore"
-- ".ruby-gemset"
-- ".ruby-version"
+- CHANGELOG.md
 - Gemfile
 - MIT-LICENSE
 - README.md
 - Rakefile
+- bin/ch2py
 - chinese_pinyin.gemspec
 - data/Mandarin.dat
 - data/pinyin-utf8.dat
@@ -35,9 +37,10 @@ files:
 - test/chinese_pinyin_test.rb
 - test/test_helper.rb
 homepage: http://github.com/flyerhzm/chinese_pinyin
-licenses: []
+licenses:
+- MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -52,9 +55,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: 1.3.6
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.4.5
-signing_key: 
+rubygems_version: 3.1.4
+signing_key:
 specification_version: 4
 summary: translate chinese hanzi to pinyin.
 test_files:

data/.ruby-gemset

@@ -1 +0,0 @@
-chinese_pinyin

data/.ruby-version

@@ -1 +0,0 @@
-ruby-2.2.0