zhongwen_tools 0.6.2 → 0.7.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 0cbbd4c2a34b34b4a989f68c60d95b03581b8c95
-  data.tar.gz: 7c5500e886bd0a24733b0cb4822b08a16b88cd28
+  metadata.gz: e932cfe269ff98dea98a88c0d1ff37961a8f376f
+  data.tar.gz: f39e6e24ec02e8f44ac16f33a2945a605dd962fe
 SHA512:
-  metadata.gz: 208dc99b54380cf448be2c35b2a20bb47a5e2b3b537f18fde291a653962297ce093266739ae8546952e126184b2cea0a3a9b3fbb9eae99383e7f380e2033055b
-  data.tar.gz: 1048a0cfbb2077702a99a1582db7576053ac28108326c47d420aabbd5cb934f90278a2c372b01591d544f2e76373539601747fd1b6a62447f82cab056e618585
+  metadata.gz: acf83d77043be54b7a8c8f24a4efce7c93a071ae6e3dab65a7a1dbaa1e38eac8e89aeadfcdd828daf5a831b23e49adc67c37991a5d71608990d3fbc9ea8880c3
+  data.tar.gz: abd8143c12ca09bb7a12c341f188232ff03d4fccf4ee5faa4c79793c4d728673cfb6d161b659fd5b4cf21d29201eca7a90596975bd759a10fead8952e3d45c4a

data/Gemfile

@@ -1,7 +1,3 @@
 source "https://rubygems.org"
 # Specify your gem's dependencies in zhongwen_tools.gemspec
 gemspec
-
-group :test do
-  gem 'pry'
-end

data/Gemfile.1.8.7

@@ -4,4 +4,5 @@ gemspec
 
 group :test do
   gem 'minitest' if RUBY_VERSION < '1.9'
+  gem 'pry'
 end

data/README.md

@@ -33,16 +33,16 @@ Add the ZhongwenTools component you need to your classes as a module.
       include ZhongwenTools::Romanization
     end
 
-    str = "ni3 hao3"  #pinyin with numbers
+    str = 'ni3 hao3'  #pinyin with numbers
     str.to_pinyin
-    #=> "nǐ hǎo"
+    #=> 'nǐ hǎo'
 
     str.to_zhuyin_fuhao
-    #=> "ㄋㄧ3 ㄏㄠ3"
+    #=> 'ㄋㄧ3 ㄏㄠ3'
 
-    mzd = "Mao Tse-tung"
+    mzd = 'Mao Tse-tung'
     mzd.to_pinyin
-    #=> "Mao Zedong"
+    #=> 'Mao Zedong'
 
 Or require the components you want.
 
@@ -113,14 +113,16 @@ simplified Chinese.
 #### Romanization
 By requiring the romanization module ZhongwenTools::String gets some
 convenience methods for dealing with romanization.
+
     require 'zhongwen_tools/romanziation'
 
     ZhongwenTools::String.to_pinyin 'ni3 hao3'
-    #=> "nǐ hǎo"
+    #=> 'nǐ hǎo'
 
 
 #### Pinyin-safe String Methods
 The following capitalization methods work for pinyin.
+
     require 'zhongwen_tools/string'
 
     ZhongwenTools::String.downcase 'Àomén'
@@ -136,6 +138,7 @@ with multibyte strings in an simple, consistent fashion regardless of
 which ruby version you are using.
 
     require 'zhongwen_tools/string'
+
     ZhongwenTools::String.chars '中文'
     #=> ['中','文']
     ZhongwenTools::String.size '中文'
@@ -149,6 +152,8 @@ which ruby version you are using.
 ### Numbers
 Functions for converting to and from Chinese numbers.
 
+    require 'zhongwen_tools/numbers'
+
     ZhongwenTools::Numbers.number_to_zht :num, 12000
     #=> '一萬二千'
     ZhongwenTools::Numbers.number_to_zhs :num, 42
@@ -163,6 +168,8 @@ Functions for converting to and from Chinese numbers.
 ### Integers
 Monkey-patch your integers for Chinese.
 
+    require 'zhongwen_tools/ingteger'
+
     class Integer
       include ZhongwenTools::Integer
     end
@@ -185,27 +192,35 @@ scripts. It **does not convert Chinese characters to pinyin** (see ZhongwenTools
     end
 
 
-    str = "ni3 hao3"
+    str = 'ni3 hao3'
+    py = 'nǐ hǎo'
 
     str.to_pinyin
-    #=> "nǐ hǎo"
+    #=> 'nǐ hǎo'
     str.to_py
-    #=> "nǐ hǎo"
-    str.to_pyn
-    #=> "ni3 hao3"
+    #=> 'nǐ hǎo'
+
+    py.to_pyn
+    #=> 'ni3 hao3'
 
     str.to_wg
-    #=> "ni3 hao3"    #Wade-Giles
+    #=> 'ni3 hao3'    #Wade-Giles
+    
     str.to_bpmf
-    #=> "ㄋㄧ3 ㄏㄠ3" #Zhuyin Fuhao, a.k.a. Bopomofo
+    #=> 'ㄋㄧ3 ㄏㄠ3' #Zhuyin Fuhao, a.k.a. Bopomofo
+
     str.to_yale
-    #=> "ni3 hau3"
+    #=> 'ni3 hau3'
+
     str.to_typy
+    #=> 'ni3 hao3'
 
     str.pyn?
     #=> true
     str.wg?
     #=> true #(There can be overlap between Wade-Giles and Pinyin)
+    str.to_py.py? 
+    #=> true
 
 ### Conversion
 Functions for converting between scripts (e.g. traditional Chinese to

data/lib/zhongwen_tools/romanization.rb

@@ -1,4 +1,4 @@
-#encoding: utf-8
+# encoding: utf-8
 require File.expand_path("../romanization/conversion_table", __FILE__)
 require File.expand_path("../romanization/detect", __FILE__)
 require File.expand_path("../romanization/pyn_to_py", __FILE__)
@@ -34,6 +34,12 @@ module ZhongwenTools
       _convert_romanization str, :typy, from
     end
 
+    def to_pyn(*args)
+      # needs to guess what the romanization type is.
+      str, from = _romanization_options(args)
+      _convert_romanization str, :pyn, from
+    end
+
     private
 
     def _romanization_options(args)
@@ -69,9 +75,9 @@ module ZhongwenTools
       end.gsub("-'","-").sub(/^'/,'')
     end
 
-    #http://en.wikipedia.org/wiki/Pinyin
-    #http://talkbank.org/pinyin/Trad_chart_IPA.php
-    #for ipa
+    # http://en.wikipedia.org/wiki/Pinyin
+    # http://talkbank.org/pinyin/Trad_chart_IPA.php
+    # for ipa
     def _to_romanization str, to, from
       convert_to = _set_type to
       convert_from = _set_type from
@@ -126,6 +132,12 @@ module ZhongwenTools
           raise NotImplementedError, 'method not implemented'
         end
         _to_romanization(str, to, from).gsub('-','')
+      elsif to == :pyn
+        if from == :py
+         _convert_pinyin_to_pyn(str)
+        else
+          raise NotImplementedError, 'method not implemented'
+        end
       else
         if from == :pyn
           _to_romanization str, to, from
@@ -135,6 +147,36 @@ module ZhongwenTools
       end
     end
 
+    def _convert_pinyin_to_pyn(pinyin)
+      # TODO: should method check to make sure pinyin is accurate?
+      pyn = []
+      words =  pinyin.split(' ')
+
+      pyn = words.map do |word|
+        pys = word.split(/['\-]/).flatten.map{|x| x.scan(PY_REGEX).map{|x| (x - [nil])[0]}}.flatten
+        current_pyn = word
+
+        pys.each do |py|
+          #take the longest pinyin match.
+          match = ZhongwenTools::Romanization::PYN_PY.values.select do |x|
+            py.include? x
+          end.sort{|x,y| x.length <=> y.length}[-1]
+
+          # Edge case.. en/eng pyn -> py conversion is one way only.
+          match = match[/(ē|é|ě|è)n?g?/].nil? ? match : match.chars[0]
+
+          replace = ZhongwenTools::Romanization::PYN_PY.find{|k,v| k if v == match}[0]
+          p = py.gsub(match, replace).gsub(/([^\d ]*)(\d)([^\d ]*)/){$1 + $3 + $2}
+
+          current_pyn = current_pyn.sub(py, p)
+        end
+
+        current_pyn.gsub("'",'')
+      end
+
+      pyn.join(' ')
+    end
+
 
     def _set_type(type)
       type = type.to_s.downcase.to_sym

data/lib/zhongwen_tools/romanization/detect.rb

@@ -1,6 +1,8 @@
+# encoding: utf-8
 module ZhongwenTools
   module Romanization
 
+    #TODO: these regexes don't deal with capital letters. Capitals will make it much more complicated.
     pyn_regexes = {
       :bpm_regex => /(miu|[pm]ou|[bpm](o|e(i|ng?)?|a(ng?|i|o)?|i(e|ng?|a[no])?|u))/,
       :f_regex => /(f(ou?|[ae](ng?|i)?|u))/,
@@ -15,8 +17,46 @@ module ZhongwenTools
       :y_regex => /y(a(o|ng?)?|e|in?g?|o(u|ng)?|u(e|a?n)?)/
     }
 
+
+    if RUBY_VERSION < '1.9'
+      py_tones = {
+        'a' => '(ā|á|ǎ|à|a)',
+        'e' => '(ē|é|ě|è|e)',
+        'i' => '(ī|í|ǐ|ì|i)',
+        'o' => '(ō|ó|ǒ|ò|o)',
+        'u' => '(ū|ú|ǔ|ù|u)',
+        'v' => '(ǖ|ǘ|ǚ|ǜ|ü)'
+      }
+      # might not need the space on the end.
+
+      PY_REGEX = /(#{pyn_regexes.map{|k,v| v.to_s[7..-2].gsub_with_hash(/[aeiouv]/,py_tones)}.join('|')}(\s\-))/
+    else
+      py_tones = {
+        'a' => '[āáǎàa]',
+        'e' => '[ēéěèe]',
+        'i' => '[īíǐìi]',
+        'o' => '[ōóǒòo]',
+        'u' => '[ūúǔùu]',
+        'v' => '[ǖǘǚǜü]'
+        #([ĀÁǍÀA][io]?|[io]?|[][āáǎàaēéěèeūúǔùu]?o?|[ĒÉĚÈE]i?|[]i?|[ŌÓǑÒO]u?|[]u?|u[āáǎàaēoēéěèe]?i?|[]e?)(n?g?r?)){1,}
+      }
+      PY_REGEX = /(#{pyn_regexes.map{|k,v| v.to_s[7..-2].gsub(/[aeiouv]/,py_tones)}.join('|')}(\s\-))/
+    end
+
     PINYIN_REGEX = /(#{pyn_regexes.values.join('|')})([1-5])?([\s\-]+)?/
-    #bpm_regex}|#{f_regex}|#{dt_regex}|#{nl_regex}|#{gkh_regex}|#{zczhch_regex}|#{ssh_regex}|#{r_regex}|#{jqx_regex}|#{aw_regex}|#{y_regex})([1-5])?([\s\-]+)?/
+
+    # Public: checks if a string is pinyin.
+    #
+    # Examples
+    #   py?('nǐ hǎo')
+    #   # => true
+    #
+    # Returns Boolean.
+    def py?(str = nil)
+      str ||= self
+
+      str.gsub(PY_REGEX, '').strip == ''
+    end
 
     # Public: checks if a string is pinyin.
     #
@@ -28,7 +68,7 @@ module ZhongwenTools
     def pyn?(str = nil)
       str ||= self
 
-      str.gsub(PINYIN_REGEX,'') == ''
+      str.gsub(PINYIN_REGEX,'').strip == ''
     end
 
     # Public: checks if a string is wade-giles.

data/lib/zhongwen_tools/string.rb

@@ -24,8 +24,13 @@ class String
     #sub only substitues the first occurence.
     self.sub(self.chars[0], self.chars[0].upcase)
   end
+
+  def scan_utf8(regex)
+    scan(regex)
+  end
 end
 
+
 module ZhongwenTools
   module String
     extend self

data/lib/zhongwen_tools/string/ruby18.rb

@@ -12,6 +12,12 @@ class String
   def reverse(str = nil)
     self.chars.reverse.join
   end
+
+  def gsub_with_hash(pattern, hash)
+    gsub(pattern) do |m|
+      hash[m]
+    end
+  end
 end
 
 module ZhongwenTools

data/lib/zhongwen_tools/version.rb

@@ -1,3 +1,3 @@
 module ZhongwenTools
-  VERSION = "0.6.2"
+  VERSION = "0.7.2"
 end

data/test/test_romanization.rb

@@ -21,10 +21,10 @@ class TestRomanization < Minitest::Test
     #assert_equal "Mao Zedong", mzd.to_pinyin(:wg)
   end
 
-  #def test_pyn
-    #skip
-    #assert_equal 'ni3 hao3', @py.to_pyn
-  #end
+  def test_pyn
+    assert_equal 'ni3 hao3', @py.to_pyn(:py)
+    assert_equal 'tian1an1men2', 'tian1an1men2'.to_py.to_pyn(:py)
+  end
 
   def test_zhuyin_fuhao
      assert_equal 'ㄋㄧ3 ㄏㄠ3', @str.to_bpmf
@@ -64,9 +64,11 @@ class TestRomanization < Minitest::Test
 
   def test_detect
     assert @str.pyn?
+    assert " #{@str}".pyn?
     refute @py.pyn?
 
     assert 'chung1 kuo2'.wg?
+    assert @py.py?
   end
 
   def setup

data/zhongwen_tools.gemspec

@@ -25,5 +25,6 @@ Gem::Specification.new do |s|
     s.add_development_dependency('simplecov-gem-adapter', '~> 1.0', '>= 1.0.1')
     s.add_development_dependency('coveralls', '~> 0.7', '>= 0.7.0')
     s.add_development_dependency('minitest', '~> 5')
+    s.add_development_dependency('pry', '~> 0.9', '>= 0.9.12')
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: zhongwen_tools
 version: !ruby/object:Gem::Version
-  version: 0.6.2
+  version: 0.7.2
 platform: ruby
 authors:
 - Steven Daniels
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-04-28 00:00:00.000000000 Z
+date: 2014-05-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -98,6 +98,26 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '5'
+- !ruby/object:Gem::Dependency
+  name: pry
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.9'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.9.12
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.9'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.9.12
 description: Chinese tools for romanization conversions and other helpful string functions
   for Chinese.
 email: