me2text-ruby 1.0.1 → 1.0.2

data/.gitignore

@@ -5,4 +5,4 @@ Gemfile.lock
 doc/*
 pkg/*
 perf/*
-
+.rbenv-version

data/README.md

@@ -94,12 +94,18 @@ TODO
 ----
 
   * Ruby 1.9 지원
+  
+Contributors
+------------
 
-Copyright and License
----------------------
+Authors ordered by first contribution.
 
-Copyright 2012 NHN Corp.
+Heungseok Do <codian@gmail.com>
+MinYoung Jung <kkungkkung@gmail.com>
 
-me2text is released under the MIT license:
+License
+-------
+
+me2text-ruby is released under the MIT license:
 
 * www.opensource.org/licenses/MIT

data/Rakefile

@@ -1 +1,11 @@
 require "bundler/gem_tasks"
+require 'rake/testtask'
+
+desc "Run unit tests"
+Rake::TestTask.new("test_units") do |t|
+	t.pattern = 'test/*_test.rb'
+	t.verbose = true
+	t.warning = true
+end
+
+task :default => :test_units

data/lib/me2text/me2text.rb

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# -*- encoding: utf-8 -*-
 
 require 'me2text/token'
 
@@ -71,6 +71,28 @@ module Me2Text
         :limit => nil,
         :link_handler => nil
       }.merge(options)
+
+      if RUBY_VERSION < '1.9'
+        begin
+          text.dup.unpack('U*')
+        rescue ArgumentError
+          raise ArgumentError.new('me2text는 유효한 UTF-8 입력만 처리 가능합니다.')
+        end
+      else
+        is_utf8 = case text.encoding
+        when Encoding::UTF_8
+          text.dup.valid_encoding?
+        when Encoding::ASCII_8BIT, Encoding::US_ASCII
+          text.dup.force_encoding(Encoding::UTF_8).valid_encoding?
+        else
+          false
+        end
+
+        raise ArgumentError.new('me2text는 유효한 UTF-8 입력만 처리 가능합니다.') unless is_utf8
+
+        text = text.force_encoding(Encoding::UTF_8)
+      end
+
       text = strip_linebreak(text) unless options[:allow_line_break]
       
       text = Token.join_tokens(Token.tokenize(text), format, options)
@@ -87,22 +109,22 @@ module Me2Text
     end
 
     def doublequotize(text) #:nodoc:
-      text.gsub(/\"([^"]*)\"/) { |s|  "“#{$1}”" }
+      text.gsub(/\"([^"]*)\"/u) { |s|  "“#{$1}”" }
     end
 
     # 라인브레이크를 <br /> 태그로 대체한다.
     def htmlize_linebreak(text) 
-      text.gsub(/\r\n/, "<br />").gsub(/\n/, "<br />").gsub(/\r/, "<br />")
+      text.gsub(/\r\n/u, "<br />").gsub(/\n/u, "<br />").gsub(/\r/u, "<br />")
     end
 
     # 컨트롤 문자를 제거한다.
     def strip_control_chars(text) 
-      text.gsub(/[[:cntrl:]]/, "")
+      text.gsub(/[[:cntrl:]]/u, "")
     end
 
     # 라인브래이크를 공백으로 변환한다
     def strip_linebreak(text) 
-      text.gsub(/\s\r\n/, "").gsub(/\r\n/, " ").gsub(/[\r\n]/, " ")
+      text.gsub(/\s\r\n/u, "").gsub(/\r\n/u, " ").gsub(/[\r\n]/u, " ")
     end
   end
 end

data/lib/me2text/string_ext.rb

@@ -1,3 +1,5 @@
+# -*- encoding: utf-8 -*-
+
 require 'me2text'
 
 module Me2Text

data/lib/me2text/token.rb

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# -*- encoding: utf-8 -*-
 
 module Me2Text
   class Token 
@@ -6,9 +6,9 @@ module Me2Text
       dquota_s = '\\xe2\\x80\\x9c|\\xe2\\x80\\x9f|\\xe2\\x9d\\x9d|\\xe2\\x80\\xb6|\\xe2\\x80\\x9d|\\x22|\\xef\\xbc\\x82'
       dquota_e = '\\xe2\\x80\\x9d|\\xe2\\x80\\x9e|\\xe2\\x9d\\x9e|\\xcb\\x9d|\\xe2\\x80\\xb3|\\xe2\\x80\\x9e|\\xe2\\x80\\x9f|\\x22|\\xef\\xbc\\x82'
       dquota_ne = '\\xe2\\x80\\x9d\\xe2\\x80\\x9e\\xe2\\x9d\\x9e\\xcb\\x9d\\xe2\\x80\\xb3\\xe2\\x80\\x9e\\xe2\\x80\\x9f\\x22\\xef\\xbc\\x82'
-      /(?:#{dquota_s})([^#{dquota_ne}]*)(?:#{dquota_e}):(http[s]?:\/\/[^\s]*)(\s|$)/
+      /(?:#{dquota_s})([^#{dquota_ne}]*)(?:#{dquota_e}):(http[s]?:\/\/[^\s]*)(\s|$)/u
     end
-    REGEX_URL = /(http[s]?:\/\/[^\s|^\'|^\"]*)([\'|\"|\s]|$)/
+    REGEX_URL = /(http[s]?:\/\/[^\s|^\'|^\"]*)([\'|\"|\s]|$)/u
     ESCAPE_CHAR = "\xc2\xa0"
 
     attr_accessor :text
@@ -71,7 +71,7 @@ module Me2Text
     end
     
     def htmlize_chars(text, options = {})
-      html_result = text.to_s.gsub(/&/, "&amp;").gsub(/</, "&lt;").gsub(/>/, "&gt;")
+      html_result = text.to_s.gsub(/&/u, "&amp;").gsub(/</u, "&lt;").gsub(/>/u, "&gt;")
       html_result = textize(html_result, options)
       html_result
     end
@@ -82,18 +82,18 @@ module Me2Text
       }.merge(options)
 
       if options[:symbolize]
-        text = text.gsub(/\.\.\./, "…").
-                    gsub(/\(TM\)/, "™").
-                    gsub(/\(R\)/, "®").
-                    gsub(/\(C\)/, "©").
-                    gsub(/--/, "—")
+        text = text.gsub(/\.\.\./u, "…").
+                    gsub(/\(TM\)/u, "™").
+                    gsub(/\(R\)/u, "®").
+                    gsub(/\(C\)/u, "©").
+                    gsub(/--/u, "—")
       end
       text
     end
 
     class << self
       def tokenize(text, options = {})
-        tokenize_me2link(text.gsub(/\\\"/, ESCAPE_CHAR), options)
+        tokenize_me2link(text.gsub(/\\\"/u, ESCAPE_CHAR), options)
       end
       
       def tokenize_me2link(text, options = {})
@@ -295,7 +295,7 @@ module Me2Text
   end
   
   class Keyword < Token 
-    KEYWORD_REGEX = /(\[([^\[\]]+)\])/
+    KEYWORD_REGEX = /(\[([^\[\]]+)\])/u
     attr_accessor :link
     
     def initialize(keyword, options)
@@ -303,7 +303,7 @@ module Me2Text
       _keyword = keyword.to_s.strip.scan(KEYWORD_REGEX)
       _keyword = _keyword.flatten[1]
 
-      raise "키워드가 없습니다." if _keyword.nil?
+      raise ArgumentError.new("키워드가 없습니다.") if _keyword.nil?
       
       @text = _keyword.gsub(ESCAPE_CHAR, "\"")
     end

data/lib/me2text/version.rb

@@ -1,3 +1,5 @@
+# -*- encoding: utf-8 -*-
+
 module Me2Text
-  VERSION = "1.0.1"
+  VERSION = "1.0.2"
 end

data/lib/me2text.rb

@@ -1,20 +1,8 @@
-# encoding: utf-8
-
-major, minor, patch = RUBY_VERSION.split('.')
-if major.to_i == 1 && minor.to_i > 8
-  raise("me2text는 ruby 1.9 이상은 현재 지원하지 않습니다.")
-else
-  # Ruby 1.8 $KCODE check.
-  unless $KCODE[0].chr =~ /u/i
-    raise("me2text를 사용하기 위해서는 $KCODE 변수를 'UTF8' 또는 'u'로 지정해야 합니다.") 
-  end
-end
-
+# -*- encoding: utf-8 -*-
 $:.push(File.expand_path("..", __FILE__))
 
 module Me2Text
 end
 
 require 'me2text/version'
-require 'me2text/me2text'
-
+require 'me2text/me2text'

data/me2text-ruby.gemspec

@@ -5,12 +5,12 @@ require "me2text/version"
 Gem::Specification.new do |s|
   s.name        = "me2text-ruby"
   s.version     = Me2Text::VERSION
-  s.authors     = ["codian"]
+  s.authors     = ["codian", 'kkung']
   s.email       = ["codian@gmail.com"]
   s.homepage    = "https://github.com/me2day/me2text-ruby"
   s.summary     = %q{me2text parser for ruby}
   s.description = %q{me2text is text format for me2day posting.
-me2text-ruby is ruby library to me2text to HTML or plain text}
+me2text-ruby is ruby library to convert me2text to HTML or plain text}
   s.rubyforge_project = "me2text-ruby"
   s.files         = Dir['{lib/**/*,test/**/*}'] +
                       %w(.gitignore me2text-ruby.gemspec Gemfile MIT-LICENSE Rakefile README.md)

data/test/{test.rb → me2text_test.rb}

@@ -1,8 +1,38 @@
-# encoding: utf-8
+# -*- encoding: utf-8 -*-
 
 require File.expand_path('../test_helper', __FILE__)
 
-class Me2TextTest < Test::Unit::TestCase  
+class Me2TextTest < Test::Unit::TestCase
+
+  if RUBY_VERSION < '1.9'
+    def test_encoding
+      #'안녕?' in EUC_KR
+      invalid_text = "\xBE\xC8\xB3\xE7?"
+      
+      assert_raise ArgumentError do
+        Me2Text.me2text(invalid_text)
+      end
+
+      assert_nothing_raised ArgumentError do
+        require 'iconv'
+        Me2Text.me2text(Iconv.conv('UTF-8', 'EUC-KR', invalid_text))
+      end
+    end
+  else
+    def test_encoding
+      #'안녕?' in EUC_KR
+      invalid_text = "\xBE\xC8\xB3\xE7?"
+      
+      assert_raise ArgumentError do
+        Me2Text.me2text(invalid_text)
+      end
+
+      assert_nothing_raised ArgumentError do
+        Me2Text.me2text(invalid_text.force_encoding(Encoding::EUC_KR).encode(Encoding::UTF_8))
+      end
+    end
+  end  
+
   def test_to_html
     cases = [
       # 일반 텍스트
@@ -30,14 +60,7 @@ class Me2TextTest < Test::Unit::TestCase
     ]
 
     cases.each_with_index do |test, index|
-      text = test[0]
-      expect = test[1]
-      result = Me2Text.me2text(text, :html)
-      if expect != result
-        flunk "TEXT:   #{text}\n" +
-              "EXPECT: #{expect}\n" +
-              "RESULT: #{result}\n"
-      end
+      assert_equal test[1], Me2Text.me2text(test[0], :html)
     end 
   end
 
@@ -50,14 +73,7 @@ class Me2TextTest < Test::Unit::TestCase
     ]
 
     cases.each_with_index do |test, index|
-      text = test[0]
-      expect = test[1]
-      result = Me2Text.me2text(text, :html, :allow_line_break => true)
-      if expect != result
-        flunk "TEXT:   #{text.inspect}\n" +
-              "EXPECT: #{expect}\n" +
-              "RESULT: #{result}\n"
-      end
+      assert_equal test[1], Me2Text.me2text(test[0], :html, :allow_line_break => true)
     end 
   end
 end

data/test/test_helper.rb

@@ -1,9 +1,4 @@
-# encoding: utf-8
-
-major, minor, patch = RUBY_VERSION.split('.')
-$KCODE = "U" if major.to_i == 1 && minor.to_i < 9
+# -*- encoding: utf-8 -*-
 
 require 'test/unit'
-require File.expand_path('../../lib/me2text', __FILE__)
-
-
+require File.expand_path('../../lib/me2text', __FILE__)

metadata

@@ -1,26 +1,27 @@
 --- !ruby/object:Gem::Specification 
 name: me2text-ruby
 version: !ruby/object:Gem::Version 
-  hash: 21
+  hash: 19
   prerelease: 
   segments: 
   - 1
   - 0
-  - 1
-  version: 1.0.1
+  - 2
+  version: 1.0.2
 platform: ruby
 authors: 
 - codian
+- kkung
 autorequire: 
 bindir: bin
 cert_chain: []
 
-date: 2012-05-21 00:00:00 Z
+date: 2012-05-22 00:00:00 Z
 dependencies: []
 
 description: |-
   me2text is text format for me2day posting.
-  me2text-ruby is ruby library to me2text to HTML or plain text
+  me2text-ruby is ruby library to convert me2text to HTML or plain text
 email: 
 - codian@gmail.com
 executables: []
@@ -35,7 +36,7 @@ files:
 - lib/me2text/token.rb
 - lib/me2text/version.rb
 - lib/me2text.rb
-- test/test.rb
+- test/me2text_test.rb
 - test/test_helper.rb
 - .gitignore
 - me2text-ruby.gemspec
@@ -77,6 +78,6 @@ signing_key:
 specification_version: 3
 summary: me2text parser for ruby
 test_files: 
-- test/test.rb
+- test/me2text_test.rb
 - test/test_helper.rb
 has_rdoc: