korean-string 0.1.0

data/.document

@@ -0,0 +1,5 @@
+README.rdoc
+lib/**/*.rb
+bin/*
+features/**/*.feature
+LICENSE

data/.gitignore

@@ -0,0 +1,21 @@
+## MAC OS
+.DS_Store
+
+## TEXTMATE
+*.tmproj
+tmtags
+
+## EMACS
+*~
+\#*
+.\#*
+
+## VIM
+*.swp
+
+## PROJECT::GENERAL
+coverage
+rdoc
+pkg
+
+## PROJECT::SPECIFIC

data/LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2009 Ben Humphreys
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.rdoc

@@ -0,0 +1,33 @@
+= korean-string
+
+Split Korean characters to individual compontents, join components together to create characters.
+
+You could use it to make some weird conjugation rules. Go wild.
+
+== Methods
+
+=== String.split_ko
+
+Return an array of arrays of Korean character components
+
+    require 'korean-string'
+    '읽어싶'.split_ko
+    => [["ㅇ", "ㅣ", "ㄺ"], ["ㅇ", "ㅓ"], ["ㅅ", "ㅣ", "ㅍ"]]
+
+=== Array.join_ko
+
+Accepts an array of character pieces
+
+    require 'korean-string'
+    [["ㅇ", "ㅣ", "ㄺ"], ["ㅇ", "ㅓ"], ["ㅅ", "ㅣ", "ㅍ"]].join_ko
+    => '읽어싶'
+
+
+== Todo
+
+Come up with other useful methods?
+
+
+== Copyright
+
+Copyright (c) 2010 Ben Humphreys. See LICENSE for details.

data/Rakefile

@@ -0,0 +1,53 @@
+require 'rubygems'
+require 'rake'
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |gem|
+    gem.name = "korean-string"
+    gem.summary = %Q{Korean string join and split}
+    gem.description = %Q{Split Korean characters to individual compontents, join components together to create characters}
+    gem.email = "benhumphreys@gmail.com"
+    gem.homepage = "http://github.com/bhumphreys/korean-string"
+    gem.authors = ["Ben Humphreys"]
+    #gem.add_development_dependency "thoughtbot-shoulda", ">= 0"
+    # gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
+  end
+  Jeweler::GemcutterTasks.new
+rescue LoadError
+  puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
+end
+
+require 'rake/testtask'
+Rake::TestTask.new(:test) do |test|
+  test.libs << 'lib' << 'test'
+  test.pattern = 'test/**/test_*.rb'
+  test.verbose = true
+end
+
+begin
+  require 'rcov/rcovtask'
+  Rcov::RcovTask.new do |test|
+    test.libs << 'test'
+    test.pattern = 'test/**/test_*.rb'
+    test.verbose = true
+  end
+rescue LoadError
+  task :rcov do
+    abort "RCov is not available. In order to run rcov, you must: sudo gem install spicycode-rcov"
+  end
+end
+
+task :test => :check_dependencies
+
+task :default => :test
+
+require 'rake/rdoctask'
+Rake::RDocTask.new do |rdoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "korean-string #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/VERSION

@@ -0,0 +1 @@
+0.1.0

data/lib/korean-string.rb

@@ -0,0 +1,112 @@
+# Originally transliterate-hacked from Perl from
+# http://blog.naver.com/PostView.nhn?blogId=mokomoji&logNo=130013133481
+#
+# For the theory of why this works, check out the W3C spec on Korean encoding
+# http://www.w3c.or.kr/i18n/hangul-i18n/ko-code.html
+# (Thanks to @ntrolls for this)
+
+$KCODE = 'UTF8'
+
+         # ㄱ      ㄲ      ㄴ      ㄷ      ㄸ      ㄹ      ㅁ      ㅂ      
+CHOSUNG = [0x3131, 0x3132, 0x3134, 0x3137, 0x3138, 0x3139, 0x3141, 0x3142,
+         # ㅃ      ㅅ      ㅆ      ㅇ      ㅈ      ㅉ      ㅊ      ㅋ      
+           0x3143, 0x3145, 0x3146, 0x3147, 0x3148, 0x3149, 0x314a, 0x314b,
+         # ㅌ      ㅍ      ㅎ
+           0x314c, 0x314d, 0x314e]
+
+           # ㅏ      ㅐ      ㅑ      ㅒ      ㅓ      ㅔ      ㅕ      ㅖ
+JWUNGSUNG = [0x314f, 0x3150, 0x3151, 0x3152, 0x3153, 0x3154, 0x3155, 0x3156,
+           # ㅗ      ㅘ      ㅙ      ㅚ      ㅛ      ㅜ      ㅝ      ㅞ      
+             0x3157, 0x3158, 0x3159, 0x315a, 0x315b, 0x315c, 0x315d, 0x315e,
+           # ㅟ      ㅠ      ㅡ      ㅢ      ㅣ
+             0x315f, 0x3160, 0x3161, 0x3162, 0x3163]
+
+            # ㄱ      ㄲ      ㄳ      ㄴ      ㄵ      ㄶ      ㄷ      ㄹ
+JONGSUNG  = [ 0,      0x3131, 0x3132, 0x3133, 0x3134, 0x3135, 0x3136, 0x3137,
+            # ㄺ      ㄻ      ㄼ      ㄽ      ㄾ      ㄿ      ㅀ      ㅁ
+              0x3139, 0x313a, 0x313b, 0x313c, 0x313d, 0x313e, 0x313f, 0x3140,
+            # ㅂ      ㅄ      ㅅ      ㅆ      ㅇ      ㅈ      ㅊ      ㅋ      
+              0x3141, 0x3142, 0x3144, 0x3145, 0x3146, 0x3147, 0x3148, 0x314a,
+            # ㅌ      ㅍ      ㅎ      ?whoops
+              0x314b, 0x314c, 0x314d, 0x314e ]
+
+
+# Not wrapping this in a module... not sure if that's a terrible idea
+
+class String
+  def split_ko
+
+    raw_chars = self.unpack("U*")
+
+    final_result = Array.new
+
+    raw_chars.each do |char|
+      result = Array.new
+      if (char >= 0xAC00 && char <= 0xD7A3)
+        # Move it down in the range
+        c = char - 0xAC00;
+
+        # Here be dragons
+        a = c.to_f / (21 * 28)
+        c = c      % (21 * 28)
+        b = c.to_f / 28
+        c = c      % 28
+
+        a = a.to_i
+        b = b.to_i
+        c = c.to_i
+
+        result.push( CHOSUNG[a], JWUNGSUNG[b] )
+
+        if c != 0
+          result.push( JONGSUNG[c] )
+        end
+      else
+        result.push(char)
+      end
+
+      final_result.push(result.pack("U*").split(''))
+    end
+
+    return final_result
+
+  end
+end
+
+
+class Array
+  # We've got our sploded array of korean bits
+  # need to put them back into Real Words
+  def join_ko
+    # http://www.w3c.or.kr/i18n/hangul-i18n/ko-code.html
+    # Leading, middle, following (optional)
+    a = self[0].unpack("U*").first
+    b = self[1].unpack("U*").first
+    c = self[2].unpack("U*").first if self[2]
+
+    offset_a = CHOSUNG.index(a)
+    if offset_a.nil?
+      raise
+    end
+    offset_b = JWUNGSUNG.index(b)
+    if offset_b.nil?
+      raise
+    end
+
+    offset_c = 0
+    if c
+      offset_c = JONGSUNG.index(c)
+      if offset_c.nil?
+        raise
+      end
+    end
+
+    raw = 0xAC00 +
+      offset_a * (21 * 28) +
+      offset_b * 28 +
+      offset_c
+
+    [ raw ].pack("U*")
+  end
+end
+

data/test/helper.rb

@@ -0,0 +1,9 @@
+require 'rubygems'
+require 'test/unit'
+
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+require 'korean-string'
+
+class Test::Unit::TestCase
+end

data/test/test_korean-string.rb

@@ -0,0 +1,38 @@
+require 'helper'
+
+class TestKoreanString < Test::Unit::TestCase
+
+  def test_split
+    assert_equal(
+      [["ㅇ", "ㅏ", "ㄴ"],
+       ["ㄴ", "ㅕ", "ㅇ"],
+       ["ㅎ", "ㅏ"],
+       ["ㅅ", "ㅔ"],
+       ["ㅇ", "ㅛ"]],
+      '안녕하세요'.split_ko
+    )
+
+    assert_equal(
+      [["ㅇ", "ㅣ", "ㄺ"], ["ㅇ", "ㅓ"], ["ㅅ", "ㅣ", "ㅍ"]],
+      '읽어싶'.split_ko
+    )
+
+    assert_equal(
+      [["ㄱ", "ㅙ", "ㄴ"], ["ㅊ", "ㅏ", "ㄶ"], ["ㅇ", "ㅏ"]],
+      '괜찮아'.split_ko
+    )
+  end
+
+  def test_join
+    assert_equal(
+      "아",
+      %w(ㅇ ㅏ).join_ko
+    )
+
+    assert_equal(
+      "일",
+      %w(ㅇ ㅣ ㄹ).join_ko
+    )
+  end
+end
+

metadata

@@ -0,0 +1,77 @@
+--- !ruby/object:Gem::Specification 
+name: korean-string
+version: !ruby/object:Gem::Version 
+  hash: 27
+  prerelease: false
+  segments: 
+  - 0
+  - 1
+  - 0
+  version: 0.1.0
+platform: ruby
+authors: 
+- Ben Humphreys
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2010-11-03 00:00:00 +09:00
+default_executable: 
+dependencies: []
+
+description: Split Korean characters to individual compontents, join components together to create characters
+email: benhumphreys@gmail.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- LICENSE
+- README.rdoc
+files: 
+- .document
+- .gitignore
+- LICENSE
+- README.rdoc
+- Rakefile
+- VERSION
+- lib/korean-string.rb
+- test/helper.rb
+- test/test_korean-string.rb
+has_rdoc: true
+homepage: http://github.com/bhumphreys/korean-string
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --charset=UTF-8
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.7
+signing_key: 
+specification_version: 3
+summary: Korean string join and split
+test_files: 
+- test/helper.rb
+- test/test_korean-string.rb