zhongwen_tools 0.18.2 → 0.18.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 47bccf56d8e66407103478019b7b7e7355a493c8
-  data.tar.gz: 355e9aa4f41356610290d76461991274d563a9ad
+  metadata.gz: 7d727c81b7c2271ab7dbd09761b085509f47e082
+  data.tar.gz: 5f96488fbcfaeb56d02ff61670c15508413ad73b
 SHA512:
-  metadata.gz: f018708bf11c96460191d42aeb1f2734708936063d05d1f55fa745d6ccf5a5e1085a5e47ff542c1387ff57b5d07700c4a723bb0f2aa05f810e6d51aced91e2d1
-  data.tar.gz: a2edcea2042ba9236a295800375618c4efc0b74d11713797bcca9e475d6a36dcd85157b31e15ca8499da8ae598aef8d8899d3198586bf8b4382ba0bd349e5404
+  metadata.gz: acc43754bdda9b9f26b1092f46bf0122bf7766e9a7e9effcf2c79afea97966bc8b7171b960089e3e83b3cf15cbfb3d6e651aedc1020c1e86726fac71ab16baa1
+  data.tar.gz: d1a828b7bcf7ed2f2c94c340ab1db739ce09723e67eeb7fdfe47b3e5cb17fa7d4dc65252d401ea1c60a682be2988e335d664d501e0fa4fc6376f831024a07a2a

data/lib/zhongwen_tools/caps.rb

@@ -14,7 +14,7 @@ module ZhongwenTools
     end
 
     def self.capitalize(str)
-      first_letter = str[/#{Regex.py}|[ĀÁǍÀĒÉĚÈĪÍǏÌŌÓǑÒ]/][0]
+      first_letter = str[/#{Regex.py}|[ĀÁǍÀĒÉĚÈĪÍǏÌŌÓǑÒ]|[a-zA-Z]/][0]
       str.sub(first_letter, ZhongwenTools::Caps.upcase(first_letter))
     end
 

data/lib/zhongwen_tools/romanization/pinyin.rb

@@ -47,7 +47,7 @@ module ZhongwenTools
       def self.split_py(str)
         words = str.split(' ')
 
-        results = words.map do |word|
+        words.flat_map do |word|
           word, is_capitalized = normalize_pinyin(word)
           word = normalize_n_g(word)
           word = normalize_n(word)
@@ -60,8 +60,6 @@ module ZhongwenTools
 
           recapitalize(result.flatten, is_capitalized)
         end
-
-        results.flatten
       end
 
       # Public: checks if a string is pinyin.
@@ -95,7 +93,7 @@ module ZhongwenTools
       def self.pyn?(str)
         # FIXME: use strip_punctuation method
         normalized_str = Caps.downcase(str.gsub(Regex.punc, '').gsub(/[\s\-]/, ''))
-        pyn_arr = split_pyn(normalized_str).map{ |p| p }
+        pyn_arr = split_pyn(normalized_str).map { |p| p }
         pyn_arr << normalized_str if pyn_arr.size == 0 && PYN_SYLLABIC_NASALS.include?(normalized_str.gsub(/[1-5]/, ''))
 
         pyn_matches_properly?(pyn_arr, normalized_str) &&
@@ -117,7 +115,7 @@ module ZhongwenTools
       end
 
       def self.are_all_pyn_syllables_complete?(pyn_arr)
-        pyns = ROMANIZATIONS_TABLE.map{ |r| r[:pyn] } + PYN_SYLLABIC_NASALS
+        pyns = ROMANIZATIONS_TABLE.map { |r| r[:pyn] } + PYN_SYLLABIC_NASALS
 
         pyn_syllables = pyn_arr.select do |p|
           pyns.include?(p.gsub(/[1-5]/, ''))
@@ -145,7 +143,7 @@ module ZhongwenTools
         #       Special Case split_py("yìnián")   # => ["yì" + "nián"]
         #                    split_py("Xīní")     # => ["Xī", "ní"]
         regex = /([#{ Regex.only_tones }])(n(#{Regex.py_tones['v']}|#{Regex.py_tones['i']}|[iu]|#{Regex.py_tones['e']}|[#{Regex.py_tones['a']}]))/
-        pinyin.gsub(regex) { "#{ $1 }-#{ $2 }" }
+        pinyin.gsub(regex) { "#{$1}-#{$2}" }
       end
 
       def self.normalize_pinyin(pinyin)
@@ -198,12 +196,11 @@ module ZhongwenTools
       end
 
       def self.current_pyn(pyn, pinyin_arr)
-        pinyin_arr.each do |pinyin|
-          replace =  pinyin_replacement(pinyin)
-          pyn.sub!(pinyin, replace)
-        end
+        replacements = pinyin_arr.map  do |pinyin|
+          [pinyin, pinyin_replacement(pinyin)]
+        end.to_h
 
-        pyn.gsub("'", '')
+        pyn.gsub(/#{pinyin_arr.join('|')}/, replacements).gsub("''", '')
       end
 
       def self.pinyin_replacement(py)
@@ -214,7 +211,7 @@ module ZhongwenTools
         match = select_pinyin_match(matches)
         replace = PYN_PY.find { |k, v| k if v == match }[0]
 
-        py.gsub(match, replace).gsub(/([^\d ]*)(\d)([^\d ]*)/){ $1 + $3 + $2 }
+        py.gsub(match, replace).gsub(/([^\d ]*)(\d)([^\d ]*)/) { $1 + $3 + $2 }
       end
 
       def self.select_pinyin_match(matches)
@@ -245,7 +242,7 @@ module ZhongwenTools
         #       And finally, correct those apostrophes at the very end.
         #       It's like magic.
         str.gsub(regex) do
-          ($3.nil? ? "#{ PYN_PY[$1] }" : ($2 == '' && %w(a e o).include?($3[0,1]))? "'#{ PYN_PY["#{ $3 }#{ $6 }"]}#{ $4 }#{ $5 }" : "#{ $2 }#{ PYN_PY["#{ $3 }#{ $6 }"] }#{ $4 }#{ $5 }") + (($7.to_s.length > 1) ? '-' : '')
+          ($3.nil? ? "#{ PYN_PY[$1] }" : ($2 == '' && %w(a e o).include?($3[0, 1])) ? "'#{ PYN_PY["#{ $3 }#{ $6 }"]}#{ $4 }#{ $5 }" : "#{ $2 }#{ PYN_PY["#{ $3 }#{ $6 }"] }#{ $4 }#{ $5 }") + (($7.to_s.length > 1) ? '-' : '')
         end.gsub("-'", '-').sub(/^'/, '')
       end
     end

data/lib/zhongwen_tools/version.rb

@@ -1,3 +1,3 @@
 module ZhongwenTools
-  VERSION = '0.18.2'
+  VERSION = '0.18.3'
 end

data/test/test_caps.rb

@@ -1,5 +1,5 @@
 # encoding: utf-8
-$:.unshift File.join(File.dirname(__FILE__),'..','lib')
+$LOAD_PATH.unshift File.join(File.dirname(__FILE__), '..', 'lib')
 
 require './test/test_helper'
 require 'zhongwen_tools/caps'
@@ -18,6 +18,7 @@ class TestCaps < Minitest::Test
   def test_capitalize
     assert_equal @caps[:c], ZhongwenTools::Caps.capitalize(@caps[:d])
     assert_equal '"Zheng4qie1"', ZhongwenTools::Caps.capitalize('"Zheng4qie1"')
+    assert_equal 'Intermediate',  ZhongwenTools::Caps.capitalize('intermediate')
   end
 
   def setup

data/test/test_pinyin.rb

@@ -28,6 +28,7 @@ class TestPinyin < Minitest::Test
     assert_equal ['nián', 'gāo'], ZhongwenTools::Romanization::Pinyin.split_py('niángāo')
     assert_equal %w(fú shè néng), ZhongwenTools::Romanization::Pinyin.split_py('fúshènéng')
     assert_equal ['sān', 'gēng'], ZhongwenTools::Romanization::Pinyin.split_py('sāngēng')
+    assert_equal ['rú', 'guǒ'], ZhongwenTools::Romanization::Pinyin.split_py('rúguǒ')
   end
 
   def test_py?
@@ -89,7 +90,8 @@ class TestPinyin < Minitest::Test
     assert_equal 'yi2ge4', ZhongwenTools::Romanization::Pinyin.to_pyn('yígè')
     assert_equal 'yi4nian2', ZhongwenTools::Romanization::Pinyin.to_pyn('yìnián', :py)
     assert_equal 'hei1hu1hu1', ZhongwenTools::Romanization::Pinyin.to_pyn('hēihūhū', :py)
-    assert_equal '"Zheng4qie1"',  ZhongwenTools::Romanization::Pinyin.to_pyn('"Zhèngqiē"', :py)
+    assert_equal '"Zheng4qie1"', ZhongwenTools::Romanization::Pinyin.to_pyn('"Zhèngqiē"', :py)
+    assert_equal 'wen4wen5', ZhongwenTools::Romanization::Pinyin.to_pyn('wènwen', :py)
   end
 
   def setup

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: zhongwen_tools
 version: !ruby/object:Gem::Version
-  version: 0.18.2
+  version: 0.18.3
 platform: ruby
 authors:
 - Steven Daniels
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-04-27 00:00:00.000000000 Z
+date: 2015-05-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake