basehangul 1.0.0 → 1.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 48909fd8600e22b74fd809e6f9e6b35bd9005dd9
-  data.tar.gz: c65e09a4a53d1ff4f362c48d40c4c030e486a665
+  metadata.gz: 5dea832635fe4ba4c9cb0e698175e776ebc273ce
+  data.tar.gz: af201548ca14b381e7cad53b6674acb988b87c79
 SHA512:
-  metadata.gz: 396ad4df9d2a499d143f2cea0f08f2960961f98a1e5a37e3c99302db8a8653bb8fd9ab0d350e33e6c4659f01e04db6b75a9ac5abffa5513e0f380b5e06aa28f8
-  data.tar.gz: 508cec650cae1100a6bae217b9c7270e856909d26f99e5857c7565a1388dea6b5b6ea32edd142584957bc78ad444e925e20c1943ffef447c2ece7840f1da76a7
+  metadata.gz: 9e02f9167a48cb7a28c3328a2a216d5b2f6ca084312c9c3df2aff4f505137139348e3295dcc857962cd9fbb62a1aab3c77e1c8b0ea3f86254bd1894b67091cd4
+  data.tar.gz: f09e00ca1d6d6745ca3ad7e511d25de23174906243e1117739feac6def022317293ebdc1449f288811cf1f85d32fad12889faa9ab6dda2ac254b0f164b1d2056

data/.rubocop.yml

@@ -1,4 +1,8 @@
 inherit_from: .rubocop_todo.yml
 
+Style/AsciiComments:
+  Exclude:
+    - 'lib/basehangul/utils.rb'
+
 Style/Encoding:
   Enabled: true

data/.rubocop_todo.yml

@@ -1,10 +1,15 @@
 # This configuration was generated by `rubocop --auto-gen-config`
-# on 2014-11-05 06:26:54 +0900 using RuboCop version 0.27.0.
+# on 2014-11-08 01:14:38 +0900 using RuboCop version 0.27.0.
 # The point is for the user to remove these configuration records
 # one by one as the offenses are removed from the code base.
 # Note that changes in the inspected code, or installation of new
 # versions of RuboCop, may require this file to be generated again.
 
-# Offense count: 2
+# Offense count: 3
 Metrics/AbcSize:
-  Max: 19
+  Max: 21
+
+# Offense count: 1
+# Configuration parameters: CountComments.
+Metrics/MethodLength:
+  Max: 15

data/CHANGELOG.md

@@ -1,5 +1,10 @@
 # Changelog
 
+## 1.1.0 (2014-11-08)
+
+- Make `BaseHangul.decode` to ignore invalid characters
+- Add `BaseHangul.strict_decode`
+
 ## 1.0.0 (2014-11-05)
 
 - First release

data/README.md

@@ -1,12 +1,13 @@
 # BaseHangul
 
+[![Gem Version](https://badge.fury.io/rb/basehangul.svg)](http://badge.fury.io/rb/basehangul)
 [![Build Status](https://travis-ci.org/yous/basehangul.svg?branch=master)](https://travis-ci.org/yous/basehangul)
 [![Dependency Status](https://gemnasium.com/yous/basehangul.svg)](https://gemnasium.com/yous/basehangul)
 [![Code Climate](https://codeclimate.com/github/yous/basehangul/badges/gpa.svg)](https://codeclimate.com/github/yous/basehangul)
 [![Coverage Status](https://img.shields.io/coveralls/yous/basehangul.svg)](https://coveralls.io/r/yous/basehangul)
 [![Inline docs](http://inch-ci.org/github/yous/basehangul.svg?branch=master)](http://inch-ci.org/github/yous/basehangul)
 
-[BaseHangul](https://github.com/koreapyj/basehangul) for Ruby. BaseHangul is an binary encoder using hangul. You can see [the specification](http://api.dcmys.jp/basehangul/) of it.
+Human-readable binary encoding, [BaseHangul](https://basehangul.github.io) for Ruby.
 
 ## Installation
 
@@ -32,10 +33,10 @@ gem install basehangul
 
 ``` ruby
 BaseHangul.encode('This is an encoded string')
-# => "넥라똔먈늴멥갯놓궂뗐밸뮤뉴뗐뀄굡덜멂똑뚤"
+# => '넥라똔먈늴멥갯놓궂뗐밸뮤뉴뗐뀄굡덜멂똑뚤'
 
 BaseHangul.decode('넥라똔먈늴멥갯놓궂뗐밸뮤뉴뗐뀄굡덜멂똑뚤')
-# => "This is an encoded string"
+# => 'This is an encoded string'
 ```
 
 ## Contributing

data/basehangul.gemspec

@@ -9,8 +9,8 @@ Gem::Specification.new do |spec|
   spec.version       = BaseHangul::Version::STRING
   spec.authors       = ['ChaYoung You']
   spec.email         = %w(yousbe@gmail.com)
-  spec.summary       = 'BaseHangul for Ruby.'
-  spec.description   = 'BaseHangul for Ruby.'
+  spec.summary       = 'Human-readable binary encoding, BaseHangul for Ruby.'
+  spec.description   = 'Human-readable binary encoding, BaseHangul for Ruby.'
   spec.homepage      = ''
   spec.license       = 'MIT'
 

data/lib/basehangul/utils.rb

@@ -7,22 +7,47 @@ module BaseHangul
     #
     # hangul - A hangul character encoded with BaseHangul.
     #
-    # Returns the Integer index of the hangul between 0 to 1027.
-    # Raises ArgumentError if the character is not valid for BaseHangul.
+    # Examples
+    #
+    #   to_index('가')
+    #   # => 0
+    #
+    #   to_index('빌')
+    #   # => 1023
+    #
+    #   to_index('빗')
+    #   # => 1027
+    #
+    #   to_index('흐')
+    #   # => -1
+    #
+    # Returns the Integer index of the hangul between 0 to 1027 or nil if the
+    #   character is invalid for BaseHangul.
     def self.to_index(hangul)
       return -1 if hangul == PADDING
       offset = hangul.encode(Encoding::EUC_KR).ord - 0xB0A1
       index = offset / 0x100 * 0x5E + offset % 0x100
-      if index < 0 || index > 1027
-        fail ArgumentError, 'Not a valid BaseHangul string'
-      end
+      return nil if index < 0 || index > 1027
       index
+    rescue Encoding::UndefinedConversionError
+      nil
     end
 
     # Convert a index to hangul character.
     #
     # index - An Integer to convert.
     #
+    # Examples
+    #
+    #   to_hangul(0)
+    #   # => '가'
+    #
+    #   to_hangul(1023)
+    #   # => '빌'
+    #
+    #   to_hangul(1027)
+    #   # => '빗'
+    #
     # Returns the String hangul for given index.
     # Raises IndexError if the index is out of range 0..1027.
     def self.to_hangul(index)
@@ -38,6 +63,20 @@ module BaseHangul
     # str  - The String to slice.
     # size - The Integer max size of each chunk.
     #
+    # Examples
+    #
+    #   chunks('foo', 1)
+    #   # => ['f', 'o', 'o']
+    #
+    #   chunks('foobarbaz', 3)
+    #   # => ['foo', 'bar', 'baz']
+    #
+    #   chunks('abcd1234AB', 4)
+    #   # => ['abcd', '1234', 'AB']
+    #
+    #   chunks('', 1)
+    #   # => []
+    #
     # Returns an Array of chunked Strings.
     # Raises ArgumentError if the size is smaller then or equal to 0.
     def self.chunks(str, size)

data/lib/basehangul/version.rb

@@ -3,6 +3,6 @@
 module BaseHangul
   # Holds the BaseHangul version information.
   module Version
-    STRING = '1.0.0'
+    STRING = '1.1.0'
   end
 end

data/lib/basehangul.rb

@@ -3,11 +3,23 @@
 require 'basehangul/version'
 require 'basehangul/utils'
 
-# Binary encoder using hangul.
+# Human-readable binary encoding.
 module BaseHangul
   # Character for padding on encoding.
   PADDING = '흐'.freeze
-  private_constant :PADDING
+
+  # Error message for invalid character.
+  MSG_INVALID_CHAR = 'Invalid character found'
+
+  # Error message for incorrect padding.
+  MSG_INVALID_PADDING = 'Invalid padding'
+
+  # Regular expression for BaseHangul.
+  REGEX_BASEHANGUL = Regexp.new('^(?:[^빎빔빕빗흐]{4})*' \
+    '(?:[^빎빔빕빗흐]흐{3}|[^빎빔빕빗흐]{2}흐{2}|' \
+    '[^빎빔빕빗흐]{3}[빎빔빕빗흐])?$').freeze
+
+  private_constant :PADDING, :MSG_INVALID_CHAR, :MSG_INVALID_PADDING
 
   # Public: Encode binary with BaseHangul.
   #
@@ -27,7 +39,8 @@ module BaseHangul
     chunks.map { |b| Utils.to_hangul(b.ljust(10, '0').to_i(2)) }.join + padding
   end
 
-  # Public: Decode BaseHangul string.
+  # Public: Decode BaseHangul string. Characters outside the BaseHangul are
+  # ignored.
   #
   # str - A String encoded with BaseHangul.
   #
@@ -36,7 +49,30 @@ module BaseHangul
     indices = str.each_char.map { |ch| Utils.to_index(ch) }
     binary = indices.map do |index|
       case index
-      when -1         then ''
+      when 0..1023    then index.to_s(2).rjust(10, '0')
+      when 1024..1027 then (index - 1024).to_s(2).rjust(2, '0')
+      end
+    end.join
+    binary = binary[0..-(binary.size % 8 + 1)]
+    [binary].pack('B*')
+  end
+
+  # Public: Decode BaseHangul string.
+  #
+  # str - A String encoded with BaseHangul.
+  #
+  # Returns the String decoded binary.
+  # Raises ArgumentError if str is invalid BaseHangul.
+  def self.strict_decode(str)
+    indices = []
+    str.each_char do |ch|
+      index = Utils.to_index(ch)
+      fail ArgumentError, MSG_INVALID_CHAR if index.nil?
+      indices << index
+    end
+    fail ArgumentError, MSG_INVALID_PADDING unless str =~ REGEX_BASEHANGUL
+    binary = indices.map do |index|
+      case index
       when 0..1023    then index.to_s(2).rjust(10, '0')
       when 1024..1027 then (index - 1024).to_s(2).rjust(2, '0')
       end

data/spec/basehangul/utils_spec.rb

@@ -19,12 +19,15 @@ RSpec.describe BaseHangul::Utils do
       expect(index).to eq(-1)
     end
 
-    it 'raises ArgumentError for invalid hangul' do
-      range = ('빙'.encode(Encoding::EUC_KR)..'힝'.encode(Encoding::EUC_KR))
-              .map { |v| v.encode(Encoding::UTF_8) }
+    it 'returns nil for invalid character' do
+      range = ["\x00", "\uFFFF",
+               'A', 'b', '1',
+               '갂', '갃', '뷁',
+               *('빙'.encode(Encoding::EUC_KR)..'힝'.encode(Encoding::EUC_KR))
+                .map { |v| v.encode(Encoding::UTF_8) }]
       range.reject { |v| v == padding }.each do |hangul|
-        expect { utils.to_index(hangul) }
-          .to raise_error(ArgumentError, 'Not a valid BaseHangul string')
+        index = utils.to_index(hangul)
+        expect(index).to eq(nil)
       end
     end
   end

data/spec/basehangul_spec.rb

@@ -17,6 +17,10 @@ RSpec.describe BaseHangul do
         expect(encoded).to eq('꺽먹꼍녜')
         encoded = basehangul.encode("123d\x00")
         expect(encoded).to eq('꺽먹꼐가')
+        encoded = basehangul.encode('1234567890')
+        expect(encoded).to eq('꺽먹께겔꼍뮷뒝낮')
+        encoded = basehangul.encode("12345678d\x00")
+        expect(encoded).to eq('꺽먹께겔꼍뮷듕가')
       end
     end
 
@@ -28,6 +32,12 @@ RSpec.describe BaseHangul do
         expect(encoded).to eq('꺽먈흐흐')
         encoded = basehangul.encode('123')
         expect(encoded).to eq('꺽먹꺄흐')
+        encoded = basehangul.encode('123456')
+        expect(encoded).to eq('꺽먹께겔꼍흐흐흐')
+        encoded = basehangul.encode('1234567')
+        expect(encoded).to eq('꺽먹께겔꼍뮨흐흐')
+        encoded = basehangul.encode('12345678')
+        expect(encoded).to eq('꺽먹께겔꼍뮷됩흐')
       end
     end
 
@@ -41,48 +51,122 @@ RSpec.describe BaseHangul do
         expect(encoded).to eq('꺽먹꼐빕')
         encoded = basehangul.encode('123g')
         expect(encoded).to eq('꺽먹꼐빗')
+        encoded = basehangul.encode('12345678d')
+        expect(encoded).to eq('꺽먹께겔꼍뮷듕빎')
+        encoded = basehangul.encode('12345678e')
+        expect(encoded).to eq('꺽먹께겔꼍뮷듕빔')
+        encoded = basehangul.encode('12345678f')
+        expect(encoded).to eq('꺽먹께겔꼍뮷듕빕')
+        encoded = basehangul.encode('12345678g')
+        expect(encoded).to eq('꺽먹께겔꼍뮷듕빗')
       end
     end
   end
 
   describe '.decode' do
-    it 'returns empty binary with empty string' do
-      decoded = basehangul.decode('')
-      expect(decoded).to eq('')
-    end
+    it_behaves_like 'a decoder', :decode
 
-    context 'when there is no padding characters' do
+    context 'when string has wrong number of padding characters' do
       it 'decodes hangul to binary' do
-        decoded = basehangul.decode('넥라똔먈늴멥갯놓궂뗐밸뮤뉴뗐뀄굡덜멂똑뚤')
-        expect(decoded).to eq('This is an encoded string')
-        decoded = basehangul.decode('꺽먹꼍녜')
+        decoded = basehangul.decode('꺽')
+        expect(decoded).to eq('1')
+        decoded = basehangul.decode('꺽흐')
+        expect(decoded).to eq('1')
+        decoded = basehangul.decode('꺽흐흐')
+        expect(decoded).to eq('1')
+        decoded = basehangul.decode('꺽흐흐흐흐')
+        expect(decoded).to eq('1')
+        decoded = basehangul.decode('꺽먈')
+        expect(decoded).to eq('12')
+        decoded = basehangul.decode('꺽먹꺄')
+        expect(decoded).to eq('123')
+        decoded = basehangul.decode('꺽먹께겔꼍')
+        expect(decoded).to eq('123456')
+        decoded = basehangul.decode('꺽먹께겔꼍뮨')
+        expect(decoded).to eq('1234567')
+        decoded = basehangul.decode('꺽먹께겔꼍뮷됩')
+        expect(decoded).to eq('12345678')
+        decoded = basehangul.decode('꺽먹꼍녜흐')
         expect(decoded).to eq('123ab')
-        decoded = basehangul.decode('꺽먹꼐가')
-        expect(decoded).to eq("123d\x00")
+        decoded = basehangul.decode('꺽먹께겔꼍뮷뒝낮흐흐')
+        expect(decoded).to eq('1234567890')
       end
     end
 
-    context 'when there are padding characters' do
-      it 'decodes hangul to binary' do
-        decoded = basehangul.decode('꺽흐흐흐')
-        expect(decoded).to eq('1')
-        decoded = basehangul.decode('꺽먈흐흐')
-        expect(decoded).to eq('12')
-        decoded = basehangul.decode('꺽먹꺄흐')
-        expect(decoded).to eq('123')
+    context 'when there are invalid characters' do
+      it 'ignores invalid characters' do
+        strings = [' 꺽먹꼍녜',
+                   '꺽먹꼍녜 ',
+                   "\n꺽\t먹\u3000꼍abc녜"]
+        strings.each do |encoded|
+          decoded = basehangul.decode(encoded)
+          expect(decoded).to eq('123ab')
+        end
+      end
+    end
+  end
+
+  describe '.strict_decode' do
+    let(:msg_invalid_char) { basehangul.const_get(:MSG_INVALID_CHAR) }
+    let(:msg_invalid_padding) { basehangul.const_get(:MSG_INVALID_PADDING) }
+
+    it_behaves_like 'a decoder', :strict_decode
+
+    context 'when string has wrong number of padding characters' do
+      it 'raises ArgumentError' do
+        strings = ['꺽', # rubocop:disable Style/WordArray
+                   '꺽흐',
+                   '꺽흐흐',
+                   '꺽흐흐흐흐',
+                   '꺽먈',
+                   '꺽먹꺄',
+                   '꺽먹께겔꼍',
+                   '꺽먹께겔꼍뮨',
+                   '꺽먹께겔껼뮷됩',
+                   '꺽먹꼍녜흐',
+                   '꺽먹께겔꼍뮷뒝낮흐흐']
+        strings.each do |encoded|
+          expect { basehangul.strict_decode(encoded) }
+            .to raise_error(ArgumentError, msg_invalid_padding)
+        end
+      end
+    end
+
+    context 'when string has characters after padding characters' do
+      it 'raises ArgumentError' do
+        strings = ['꺽흐꺽흐흐흐', # rubocop:disable Style/WordArray
+                   '꺽흐흐흐꺽흐흐흐',
+                   '꺽먹꺄흐꺽',
+                   '꺽먹께흐겔꼍흐흐흐',
+                   '꺽먹꼐흐꺽먹꼐빎']
+        strings.each do |encoded|
+          expect { basehangul.strict_decode(encoded) }
+            .to raise_error(ArgumentError, msg_invalid_padding)
+        end
+      end
+    end
+
+    context 'when string has special characters with wrong position' do
+      it 'raises ArgumentError' do
+        strings = ['꺽먹꼐빎꺽흐흐흐', # rubocop:disable Style/WordArray
+                   '꺽먹빎',
+                   '꺽먹빎흐']
+        strings.each do |encoded|
+          expect { basehangul.strict_decode(encoded) }
+            .to raise_error(ArgumentError, msg_invalid_padding)
+        end
       end
     end
 
-    context 'when there are special characters' do
-      it 'decodes hangul to binary 'do
-        decoded = basehangul.decode('꺽먹꼐빎')
-        expect(decoded).to eq('123d')
-        decoded = basehangul.decode('꺽먹꼐빔')
-        expect(decoded).to eq('123e')
-        decoded = basehangul.decode('꺽먹꼐빕')
-        expect(decoded).to eq('123f')
-        decoded = basehangul.decode('꺽먹꼐빗')
-        expect(decoded).to eq('123g')
+    context 'when there are invalid characters' do
+      it 'raises ArgumentError' do
+        strings = [' 꺽먹꼍녜',
+                   '꺽먹꼍녜 ',
+                   "\n꺽\t먹\u3000꼍abc녜"]
+        strings.each do |encoded|
+          expect { basehangul.strict_decode(encoded) }
+            .to raise_error(ArgumentError, msg_invalid_char)
+        end
       end
     end
   end

data/spec/support/shared_decode.rb

@@ -0,0 +1,65 @@
+# encoding: utf-8
+
+RSpec.shared_examples 'a decoder' do |method|
+  subject(:decode) { described_class.method(method) }
+
+  describe ".#{method}" do
+    it 'returns empty binary with empty string' do
+      decoded = decode.call('')
+      expect(decoded).to eq('')
+    end
+
+    context 'when there is no padding characters' do
+      it 'decodes hangul to binary' do
+        decoded = decode.call('넥라똔먈늴멥갯놓궂뗐밸뮤뉴뗐뀄굡덜멂똑뚤')
+        expect(decoded).to eq('This is an encoded string')
+        decoded = decode.call('꺽먹꼍녜')
+        expect(decoded).to eq('123ab')
+        decoded = decode.call('꺽먹꼐가')
+        expect(decoded).to eq("123d\x00")
+        decoded = decode.call('꺽먹께겔꼍뮷뒝낮')
+        expect(decoded).to eq('1234567890')
+        decoded = decode.call('꺽먹께겔꼍뮷듕가')
+        expect(decoded).to eq("12345678d\x00")
+      end
+    end
+
+    context 'when there are padding characters' do
+      it 'decodes hangul to binary' do
+        decoded = decode.call('꺽흐흐흐')
+        expect(decoded).to eq('1')
+        decoded = decode.call('꺽먈흐흐')
+        expect(decoded).to eq('12')
+        decoded = decode.call('꺽먹꺄흐')
+        expect(decoded).to eq('123')
+        decoded = decode.call('꺽먹께겔꼍흐흐흐')
+        expect(decoded).to eq('123456')
+        decoded = decode.call('꺽먹께겔꼍뮨흐흐')
+        expect(decoded).to eq('1234567')
+        decoded = decode.call('꺽먹께겔꼍뮷됩흐')
+        expect(decoded).to eq('12345678')
+      end
+    end
+
+    context 'when there are special characters' do
+      it 'decodes hangul to binary 'do
+        decoded = decode.call('꺽먹꼐빎')
+        expect(decoded).to eq('123d')
+        decoded = decode.call('꺽먹꼐빔')
+        expect(decoded).to eq('123e')
+        decoded = decode.call('꺽먹꼐빕')
+        expect(decoded).to eq('123f')
+        decoded = decode.call('꺽먹꼐빗')
+        expect(decoded).to eq('123g')
+        decoded = decode.call('꺽먹께겔꼍뮷듕빎')
+        expect(decoded).to eq('12345678d')
+        decoded = decode.call('꺽먹께겔꼍뮷듕빔')
+        expect(decoded).to eq('12345678e')
+        decoded = decode.call('꺽먹께겔꼍뮷듕빕')
+        expect(decoded).to eq('12345678f')
+        decoded = decode.call('꺽먹께겔꼍뮷듕빗')
+        expect(decoded).to eq('12345678g')
+      end
+    end
+  end
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: basehangul
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 1.1.0
 platform: ruby
 authors:
 - ChaYoung You
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-11-04 00:00:00.000000000 Z
+date: 2014-11-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -80,7 +80,7 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '0.9'
-description: BaseHangul for Ruby.
+description: Human-readable binary encoding, BaseHangul for Ruby.
 email:
 - yousbe@gmail.com
 executables: []
@@ -106,6 +106,7 @@ files:
 - spec/basehangul_spec.rb
 - spec/spec_helper.rb
 - spec/support/coverage.rb
+- spec/support/shared_decode.rb
 homepage: ''
 licenses:
 - MIT
@@ -129,10 +130,11 @@ rubyforge_project:
 rubygems_version: 2.4.2
 signing_key: 
 specification_version: 4
-summary: BaseHangul for Ruby.
+summary: Human-readable binary encoding, BaseHangul for Ruby.
 test_files:
 - spec/basehangul/utils_spec.rb
 - spec/basehangul/version_spec.rb
 - spec/basehangul_spec.rb
 - spec/spec_helper.rb
 - spec/support/coverage.rb
+- spec/support/shared_decode.rb