gimchi 0.1.8 → 0.1.9

data/README.ko.markdown

@@ -71,10 +71,16 @@ kc.partial?                # true
 kc = ko.korean_char "한"
 
 # Array of Gimchi::Korean::Char's
-arr = ko.dissect '이것은 한글입니다.'
+arr = ko.convert '이것은 한글입니다.'
   # [이, 것, 은, " ", 한, 글, 입, 니, 다, "."]
 
 arr[0].class               # Gimchi::Korean::Char
+
+# Dissects given String
+arr = ko.dissect '이것은 한글입니다.'
+  # ["ㅇ", "ㅣ", "ㄱ", "ㅓ", "ㅅ", "ㅇ", "ㅡ", "ㄴ", " ", 
+  #  "H", "a", "n", "g", "u", "l", " ", "ㅇ", "ㅣ", "ㅂ",
+  #  "ㄴ", "ㅣ", "ㄷ", "ㅏ", "."]
 ```
 
 ### 숫자 읽기

data/README.markdown

@@ -70,10 +70,16 @@ kc.partial?                # true
 kc = ko.korean_char "한"
 
 # Array of Gimchi::Korean::Char's
-arr = ko.dissect '이것은 한글입니다.'
+arr = ko.convert '이것은 한글입니다.'
   # [이, 것, 은, " ", 한, 글, 입, 니, 다, "."]
 
 arr[0].class               # Gimchi::Korean::Char
+
+# Dissects given String
+arr = ko.dissect '이것은 한글입니다.'
+  # ["ㅇ", "ㅣ", "ㄱ", "ㅓ", "ㅅ", "ㅇ", "ㅡ", "ㄴ", " ", 
+  #  "H", "a", "n", "g", "u", "l", " ", "ㅇ", "ㅣ", "ㅂ",
+  #  "ㄴ", "ㅣ", "ㄷ", "ㅏ", "."]
 ```
 
 ### Reading numbers in Korean

data/lib/gimchi.rb

@@ -6,4 +6,6 @@ require 'gimchi/korean'
 require 'gimchi/char'
 require 'gimchi/pronouncer'
 
-require 'gimchi/patch_1.8' if RUBY_VERSION =~ /^1.8/
+if RUBY_VERSION =~ /^1\.8\./
+  require 'gimchi/patch_1.8' 
+end

data/lib/gimchi/korean.rb

@@ -51,7 +51,7 @@ class Korean
   # Checks if the given character is a korean character.
   # @param [String] ch A string of size 1
   def korean_char? ch
-    raise ArgumentError.new('Lengthy input') if ch.length > 1
+    raise ArgumentError.new('Lengthy input') if str_length(ch) > 1
 
     complete_korean_char?(ch) || 
       (chosungs + jungsungs + jongsungs).include?(ch)
@@ -62,7 +62,7 @@ class Korean
   # "Complete" Korean character must have chosung and jungsung, with optional jongsung.
   # @param [String] ch A string of size 1
   def complete_korean_char? ch
-    raise ArgumentError.new('Lengthy input') if ch.length > 1
+    raise ArgumentError.new('Lengthy input') if str_length(ch) > 1
 
     # Range of Korean chracters in Unicode 2.0: AC00(가) ~ D7A3(힣)
     ch.unpack('U').all? { | c | c >= 0xAC00 && c <= 0xD7A3 }
@@ -71,9 +71,18 @@ class Korean
   # Splits the given string into an array of Korean::Char's and Strings of length 1.
   # @param [String] str Input string.
   # @return [Array] Mixed array of Korean::Char instances and Strings of length 1 (for non-korean characters)
-  def dissect str
+  def convert str
     str.each_char.map { |c| 
-      korean_char?(c) ? Korean::Char.new(self, c) : c
+      korean_char?(c) ? kchar(c) : c
+    }
+  end
+
+  # Splits the given string into an array of Korean character components
+  # @param [String] str Input string.
+  # @return [Array] Array of Korean character components
+  def dissect str
+    str.each_char.inject([]) { |arr, c| 
+      arr += korean_char?(c) ? kchar(c).to_a.compact : [c]
     }
   end
 
@@ -155,7 +164,7 @@ class Korean
     romanization = ""
 
     romanize_chunk = lambda do | chunk |
-      dissect(chunk).each do | kc |
+      convert(chunk).each do | kc |
         kc.to_a.each_with_index do | comp, idx |
           next if comp.nil?
           comp = rdata[idx][comp] || comp
@@ -187,6 +196,10 @@ class Korean
   end
 
 private
+  def str_length str
+    str.length
+  end
+
   def read_number_sub num, next_char
     nconfig = config['number']
 

data/lib/gimchi/patch_1.8.rb

@@ -2,25 +2,6 @@ $KCODE = 'U'
 
 module Gimchi
 class Korean
-  # Checks if the given character is a korean character.
-  # @param [String] ch A string of size 1
-  def korean_char? ch
-    raise ArgumentError.new('Lengthy input') if str_length(ch) > 1
-
-    complete_korean_char?(ch) || 
-      (chosungs + jungsungs + jongsungs).include?(ch)
-  end
-
-  # Checks if the given character is a "complete" korean character.
-  # "Complete" Korean character must have chosung and jungsung, with optional jongsung.
-  # @param [String] ch A string of size 1
-  def complete_korean_char? ch
-    raise ArgumentError.new('Lengthy input') if str_length(ch) > 1
-
-    # Range of Korean chracters in Unicode 2.0: AC00(가) ~ D7A3(힣)
-    ch.unpack('U').all? { | c | c >= 0xAC00 && c <= 0xD7A3 }
-  end
-
 private
   def str_length str
     str.scan(/./mu).length

data/lib/gimchi/pronouncer.rb

@@ -17,7 +17,7 @@ class Korean
               (options[:pronounce_each_char] ? '1' : '2')] - options[:except]
 
       # Dissecting
-      @chars = @korean.dissect str
+      @chars = @korean.convert str
       @orig_chars = @chars.dup
 
       # Padding
@@ -299,7 +299,7 @@ class Korean
 
       word = @kc.to_s + @next_kc.to_s
       if map.keys.include? word
-        new_char = @korean.dissect(map[word].scan(/./mu)[1])[0]
+        new_char = @korean.kchar(map[word].scan(/./mu)[1])
         @next_kc.chosung = new_char.chosung
         @next_kc.jongsung = new_char.jongsung
 

data/test/test_gimchi.rb

@@ -52,10 +52,19 @@ class TestGimchi < Test::Unit::TestCase
 		assert_raise(ArgumentError) { ko.korean_char?('두자') }
 	end
 
-	def test_dissect
+  def test_dissect
 		ko = Gimchi::Korean.new
 
-		arr = ko.dissect '이것은 한글입니다.'
+		arr = ko.dissect '이것은 Hangul 입니다.'
+    assert_equal ["ㅇ", "ㅣ", "ㄱ", "ㅓ", "ㅅ", "ㅇ", "ㅡ", "ㄴ", " ", 
+                  "H", "a", "n", "g", "u", "l", " ", "ㅇ", "ㅣ", "ㅂ",
+                  "ㄴ", "ㅣ", "ㄷ", "ㅏ", "."], arr
+  end
+
+	def test_convert
+		ko = Gimchi::Korean.new
+
+		arr = ko.convert '이것은 한글입니다.'
 		# [이, 것, 은, " ", 한, 글, 입, 니, 다, "."]
 
 		assert_equal 10, arr.length

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: gimchi
 version: !ruby/object:Gem::Version
-  version: 0.1.8
+  version: 0.1.9
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2011-12-02 00:00:00.000000000 Z
+date: 2012-02-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
-  requirement: &2152021800 !ruby/object:Gem::Requirement
+  requirement: &2158357040 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -21,10 +21,10 @@ dependencies:
         version: 1.0.0
   type: :development
   prerelease: false
-  version_requirements: *2152021800
+  version_requirements: *2158357040
 - !ruby/object:Gem::Dependency
   name: jeweler
-  requirement: &2152177100 !ruby/object:Gem::Requirement
+  requirement: &2158358840 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -32,10 +32,10 @@ dependencies:
         version: 1.5.2
   type: :development
   prerelease: false
-  version_requirements: *2152177100
+  version_requirements: *2158358840
 - !ruby/object:Gem::Dependency
   name: rcov
-  requirement: &2152174620 !ruby/object:Gem::Requirement
+  requirement: &2158315180 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -43,10 +43,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *2152174620
+  version_requirements: *2158315180
 - !ruby/object:Gem::Dependency
   name: ansi
-  requirement: &2152190900 !ruby/object:Gem::Requirement
+  requirement: &2154666280 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -54,7 +54,7 @@ dependencies:
         version: 1.2.2
   type: :development
   prerelease: false
-  version_requirements: *2152190900
+  version_requirements: *2154666280
 description: Gimchi knows how to pronounce Korean strings and how to write them in
   roman alphabet.
 email: junegunn.c@gmail.com
@@ -93,7 +93,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: -4230473525462168510
+      hash: -4061568131035276090
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
@@ -102,7 +102,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.10
+rubygems_version: 1.8.15
 signing_key: 
 specification_version: 3
 summary: Gimchi reads Korean.