zhongwen_tools 0.18.0 → 0.18.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 225b43aacf009731b4034a754af359efd7d067d1
-  data.tar.gz: d65490aa4067bbedf88e2805d7635bb694261bbe
+  metadata.gz: abe0b5477d8f04c2cabfe1054feffa3d1994b9d2
+  data.tar.gz: a14a4bc66804d0cbe0e3892ec48639384ae0f9bf
 SHA512:
-  metadata.gz: 14e73ad7b0b16325186b0643202416957605a0726596e44db660ba324c72685393b47c705fc40869cac9cf9815de533bff985e9daa36d903fe1dddc45587579a
-  data.tar.gz: 17ed1d4fbce22e1d13f8df22a67f716a85668efa9bd00ad6d6d89dada1f8d47320dce4b207119242cb43ddbc4ec3525a528b424a851bd70398bfa039c23ed737
+  metadata.gz: 34c8c883922b2e7cf314a6866bb54f6bc4462225492449699e70f65ccf1bd364be3cf9988a2d18edd08be1103703831e81de999dfb31a87c14dad5e1ccabaf8a
+  data.tar.gz: 23c65688e09fa36a15ef0c2add20bee70c0ce167072f73a043fc68bd34b00b5475cada95909956643855a3bb57c1f36f52e8dadb6aa7f40d85816f443f22f9df

data/README.md

@@ -5,7 +5,7 @@ Methods for dealing with Chinese.
 Status](https://img.shields.io/travis/stevendaniels/zhongwen_tools.svg?style=flat-square)](https://travis-ci.org/stevendaniels/zhongwen_tools) [![Dependency Status](https://img.shields.io/gemnasium/stevendaniels/zhongwen_tools.svg?style=flat-square)](https://gemnasium.com/stevendaniels/zhongwen_tools) [![Code Climate](https://img.shields.io/codeclimate/github/stevendaniels/zhongwen_tools.svg?style=flat-square)](https://codeclimate.com/github/stevendaniels/zhongwen_tools) [![Coverage Status](https://img.shields.io/coveralls/stevendaniels/zhongwen_tools.svg?style=flat-square)](https://coveralls.io/r/stevendaniels/zhongwen_tools)
 [![Gem Version](https://img.shields.io/gem/v/zhongwen_tools.svg?style=flat-square)](http://badge.fury.io/rb/zhongwen_tools)
 
-##INSTALLATION
+## Installation
 
 Install as a gem
 

data/lib/zhongwen_tools/regex.rb

@@ -1,5 +1,4 @@
 # encoding: utf-8
-
 module ZhongwenTools
   module Regex
     def self.pyn
@@ -7,12 +6,12 @@ module ZhongwenTools
     end
 
     def self.py
-      # FIXME: need to detect Ālābó
       # ([ĀÁǍÀA][io]?|[io]?|[][āáǎàaēéěèeūúǔùu]?o?|[ĒÉĚÈE]i?|[]i?|[ŌÓǑÒO]u?|[]u?|u[āáǎàaēoēéěèe]?i?|[]e?)(n?g?r?)){1,}
-      @py ||= /(#{pyn_regexes.map{|k,v| v.to_s[7..-2].gsub(/[aeiouv]/,py_tones)}.join('|')}([\s\-])?)/
+      @py ||= /(#{pyn_regexes.map { |_k, v| v.to_s[7..-2].gsub(/[aeiouv]/, py_tones) }.join('|')}([\s\-])?)/
     end
 
     def self.pinyin_num
+      # FIXME: n?g? might need to be replaced with (ng|n)?
       /(([BPMFDTNLGKHZCSRJQXWYbpmfdtnlgkhzcsrjqxwy]?[h]?)(A[io]?|a[io]?|i[aeu]?o?|Ei?|ei?|Ou?|ou?|u[aoe]?i?|ve?)?(n?g?)(r?)([1-5])(\-+)?)/
     end
 
@@ -86,12 +85,12 @@ module ZhongwenTools
       {
         nl_regex: /([nN]eng?|[lnLN](a(i|ng?|o)?|e(i|ng)?|i(ang|a[on]?|e|ng?|u)?|o(ng?|u)|u(o|i|an?|n)?|ve?))/,
         bpm_regex: /([mM]iu|[pmPM]ou|[bpmBPM](o|e(i|ng?)?|a(ng?|i|o)?|i(e|ng?|a[no])?|u))/,
-        y_regex: /[yY](a(o|ng?)?|e|i(n|ng)?|o(u|ng)?|u(e|a?n)?)/,
+        y_regex: /[yY](a(o|ng?)?|e|i(ng|n)?|o(u|ng)?|u(e|a?n)?)/,
         f_regex: /([fF](ou?|[ae](ng?|i)?|u))/,
         dt_regex: /([dD](e(i|ng?)|i(a[on]?|u))|[dtDT](a(i|ng?|o)?|e(i|ng)?|i(a[on]?|e|ng|u)?|o(ng?|u)|u(o|i|an?|n)?))/,
         gkh_regex: /([ghkGHK](a(i|ng?|o)?|e(i|ng?)?|o(u|ng)|u(a(i|ng?)?|i|n|o)?))/,
         zczhch_regex: /([zZ]h?ei|[czCZ]h?(e(ng?)?|o(ng?|u)?|ao|u?a(i|ng?)?|u?(o|i|n)?))/,
-        ssh_regex: /([sS]ong|[sS]hua(i|ng?)?|[sS]hei|[sS][h]?(a(i|ng?|o)?|en?g?|ou|u(a?n|o|i)?|i))/,
+        ssh_regex: /([sS]ong|[sS]hua(i|ng?)?|[sS]hei|[sS][h]?(a(i|ng?|o)?|e(ng|n)?|ou|u(a?n|o|i)?|i))/,
         r_regex: /([rR]([ae]ng?|i|e|ao|ou|ong|u[oin]|ua?n?))/,
         jqx_regex: /([jqxJQX](i(a(o|ng?)?|[eu]|ong|ng?)?|u(e|a?n)?))/,
         aeo_regex: /(([aA](i|o|ng?)?|[oO]u?|[eE](i|ng?|r)?))/,

data/lib/zhongwen_tools/romanization/pinyin.rb

@@ -49,14 +49,18 @@ module ZhongwenTools
 
         results = words.map do |word|
           word, is_capitalized = normalize_pinyin(word)
-          # NOTE: Special Case "fǎnguāng" should be "fǎn" + "guāng"
-          #       Special Case "yìnián" should be "yì" + "nián"
-          word = word.gsub('ngu', 'n-gu')
-          word = word.gsub(/([#{ Regex.only_tones }])(ni[#{ Regex.py_tones['a'] }])/){ "#{ $1 }-#{ $2 }" }
+          # NOTE: Special Case split_py("fǎnguāng") # => ["fǎn" + "guāng"]
+          #       Special Case split_py("yìnián")   # => ["yì" + "nián"]
+          #                    split_py("Xīní")     # => ["Xī", "ní"]
+          word = word.gsub(/(n)(g(#{ Regex.py_tones['o'] }|u))/){ "#{ $1 }-#{ $2 }" }
+          word = word.gsub(/([#{ Regex.only_tones }])(n(#{ Regex.py_tones['v'] }|#{ Regex.py_tones['i'] }|[iu][#{ Regex.py_tones['a'] }]))/){ "#{ $1 }-#{ $2 }" }
           result = word.split(/['\-]/).flatten.map do |x|
             find_py(x)
           end
 
+          # NOTE: Special Case split_py('wányìr')   # => ['wán', 'yì', 'r']
+          result << 'r' unless word[/(.*[^#{ Regex.py_tones['e'] }.])(r)$/].nil?
+
           recapitalize(result.flatten, is_capitalized)
         end
 

data/lib/zhongwen_tools/version.rb

@@ -1,3 +1,3 @@
 module ZhongwenTools
-  VERSION = '0.18.0'
+  VERSION = '0.18.1'
 end

data/test/test_pinyin.rb

@@ -16,6 +16,14 @@ class TestPinyin < Minitest::Test
     end
 
     assert_equal ['fǎn', 'guāng', 'jìng'], ZhongwenTools::Romanization::Pinyin.split_py('fǎnguāngjìng')
+    assert_equal ['Yīng', 'guó'], ZhongwenTools::Romanization::Pinyin.split_py('Yīngguó')
+    assert_equal ['Xī', 'ní'], ZhongwenTools::Romanization::Pinyin.split_py('Xīní')
+    assert_equal ['bàn', 'gōng', 'lóu'], ZhongwenTools::Romanization::Pinyin.split_py('bàngōnglóu')
+    assert_equal ['jì', 'nǚ'], ZhongwenTools::Romanization::Pinyin.split_py('jìnǚ')
+    assert_equal ['sè', 'guǐ'], ZhongwenTools::Romanization::Pinyin.split_py('sèguǐ')
+    assert_equal ['qǔ', 'nuǎn'], ZhongwenTools::Romanization::Pinyin.split_py('qǔnuǎn')
+    assert_equal ['wán', 'yì', 'r'], ZhongwenTools::Romanization::Pinyin.split_py('wányìr')
+    assert_equal ['yīng', "ér"], ZhongwenTools::Romanization::Pinyin.split_py("yīng'ér")
   end
 
   def test_py?

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: zhongwen_tools
 version: !ruby/object:Gem::Version
-  version: 0.18.0
+  version: 0.18.1
 platform: ruby
 authors:
 - Steven Daniels
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-03-15 00:00:00.000000000 Z
+date: 2015-04-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -233,7 +233,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: zhongwen_tools
-rubygems_version: 2.2.2
+rubygems_version: 2.4.5
 signing_key: 
 specification_version: 4
 summary: Zhongwen Tools provide romanization conversions and helper methods for Chinese.