tibetan 0.1.1 → 0.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ba53668c3dc2032bc210c35ee0d082c6a3c6f366ec86ecb682e0242e8084b2be
-  data.tar.gz: 0f9b98b0a5fa154ed9cf8b9b2c3e27c19645d493b73234c1260efff97024d2c6
+  metadata.gz: 6a99a8e45fb7a5b6fed9a82889c461a1ceec66df63086ec14e6ae60c784ae3c3
+  data.tar.gz: ba0c75c246e09eea0ea54c4838854e419954c7b8aef1f3ed6edcd6b6beca3b80
 SHA512:
-  metadata.gz: 90be6411bfb7eda39aa4dc52911a873af4e29e62c4274dedb6faad400ee5fba5ef422cad2e01a83c0758b7b356e88682c4834e2967d02b1547cc6af8582c2753
-  data.tar.gz: 72a3e240523afe6011d3eba406af85cd8914c41c8b52786c9969ae0c7ecf370fe41f883e95fd4c5c6331cff01fc81ca61e3bf455d9084d106ecb12d7a93a4a57
+  metadata.gz: a9c5c6085a9feada4da87b7017efc377cf25bbe530d45834eaf84d5ba781229df1ddf8fc7be515a911a1d4556ec879740830a871212b6a9dfb648c60221b1c62
+  data.tar.gz: 8cf0da67912ae5beedb1a2eda338b8477816d4d1627328876cc5f4cdc3debb915a9912fbafed71de00f9d57be2800174f75bd03a4685f536fa36f6b2c900215d

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    tibetan (0.1.1)
+    tibetan (0.1.2)
 
 GEM
   remote: https://rubygems.org/

data/README.md

@@ -1,6 +1,6 @@
-# Tibetan
+# Tibetan -> Wylie
 
-Romanization of Tibetan. It transliterates Tibetan text to the Roman (Latin) script.
+Romanization of Tibetan. It transliterates Tibetan text to the Latin script using THL EWTS (Extended Wylie Transliteration Scheme).
 
 ## Installation
 
@@ -27,12 +27,16 @@ require "tibetan"
 And then
 
 ```ruby
-Tibetan.transliterate("བོད་སྐད་")
+Tibetan.transliterate("བོད་སྐད་") # => "bod skad"
+Tibetan.transliterate("༡༢༣") # => "123"
+Tibetan.transliterate("༪") # => "0.5"
 ```
 or
 
 ```ruby
-Tibetan.t("བོད་སྐད་")
+Tibetan.t("བོད་སྐད་") # => "bod skad"
+Tibetan.t("༡༢༣") # => "123"
+Tibetan.t("༪") # => "0.5"
 ```
 
 ## Development

data/lib/tibetan/version.rb

@@ -1,3 +1,3 @@
 module Tibetan
-  VERSION = "0.1.1"
+  VERSION = "0.1.2"
 end

data/lib/tibetan.rb

@@ -123,13 +123,42 @@ module Tibetan
     "ླྀ"  => "ḷ",
     "ཹ" => "ḹ",
   }
+  
+  CONSONANTS = %w(ཀ ཁ ག ང ཅ ཆ ཇ ཉ ཏ ཐ ད ན པ ཕ བ མ ཙ ཚ ཛ ཝ ཞ ཟ འ ཡ ར ལ ཤ ས ཧ)
+  SUBSCRIPTS = %w(ྐ ྑ ྒ ྔ ྕ ྖ ྗ ྙ ྟ ྠ ྡ ྣ ྤ ྥ ྦ ྨ ྩ ྪ ྫ ྭ ྮ ྯ ྰ ྱ ྲ ླ ྴ ྶ ྷ)
+  VOWELS = %w(ྸ  ི  ུ  ེ  ོ a)
+  SEP = "་"
+  DEFAULT_VOWEL = "a"
 
   class << self
     def transliterate(string="", to=:tibetan)
+      string = string.to_s
+      
+      # Split long phrase into small parts and transliterate separately
+      if string.split(SEP).size > 1
+        string = string.split(SEP).map do |str|
+          transliterate(str)
+        end.join(SEP)
+      end
+      
+      insert_default_vowel!(string)
+
       character_table = Module.const_get(to.to_s.capitalize)::CHARACTER_TABLE
-      string.to_s.gsub(/#{Regexp.union(character_table.keys).source}/i, character_table)
+      string.to_s.gsub(/#{Regexp.union(character_table.keys).source}/i, character_table)      
     end
     alias_method :t, :transliterate
-  end
 
+    def insert_default_vowel!(string="")
+      # 1. after subscript
+      if (string.chars & VOWELS).empty?
+        index = string.rindex(/#{SUBSCRIPTS.join('|')}/)
+        string = string.insert(index+1, DEFAULT_VOWEL) unless index.nil?
+      end
+      # 2. after consonant, if not added in 1st step
+      if (string.chars & VOWELS).empty? && (string.chars & CONSONANTS).any?
+        index = string.size > 2 ? 1 : 0
+        string = string.insert(index+1, DEFAULT_VOWEL) unless index.nil?
+      end
+    end
+  end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: tibetan
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.1.2
 platform: ruby
 authors:
 - rovetz
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2018-09-28 00:00:00.000000000 Z
+date: 2018-10-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler