jis2euc 0.0.1 → 0.0.2

data/README

@@ -0,0 +1,37 @@
+ARIB is using a bunch of encodings when transmitting the text information, such as EPG, cc and BML text encoding. Control code is used to switch the encoding. This gem is used to convent the text information to standard EUC-JP encoding.  
+
+
+Examples : 
+
+require 'jis2euc'
+
+raw = "48 56 41 48 46 62 4d 46 e 32 89 2d 8a 1b 24 3b "
+s = raw.split.map  {|t| ("0x"+t).to_i(16)}.inject("") {|p,c| p << c.chr} 
+
+euc_s = Jis2euc.jis2euc(s,true)  #set the 2nd parameter to ture will enable debug information 
+
+
+#output debug information 
+convert following string to euc :
+48 56 41 48 46 62 4d 46 e 32 89 2d 8a 1b 24 3b 
+c1 : 48     ->Char-> kanji1     , 2
+番
+c1 : 41     ->Char-> kanji1     , 2
+番組
+c1 : 46     ->Char-> kanji1     , 2
+番組内
+c1 : 4d     ->Char-> kanji1     , 2
+番組内容
+c1 : e     ->Is CTL
+LS1 : GL=>G1, locking shift
+c1 : 32     ->Char-> eisu       , 1
+c1 : 89     ->Is CTL
+ingor
+c1 : 2d     ->Char-> eisu       , 1
+c1 : 8a     ->Is CTL
+ignor
+c1 : 1b     ->Is CTL
+ESC ..
+-> CTL 0x24  Type 3b
+番組内容２―
+

data/lib/jis2euc.rb

@@ -3,9 +3,11 @@ require File.join(File.dirname(__FILE__),'jis2euc/libjis2euc')
 
 
 module Jis2euc
-  # Your code goes here...
-  def self.jis2euc s
-	 arib_jis_to_euc s
+   #
+   # set verbose to true will print out the detail parse and conversion information
+   # 
+  def self.jis2euc s ,verbose = false
+	 arib_jis_to_euc s , verbose
 end
 
   def self.euc2utf8 s

data/lib/jis2euc/jis8ctl.rb

@@ -100,7 +100,9 @@ $encoding_mapping = {
 
 class Jis8charset
 
-	#TODO : make it singleton
+	
+  include Singleton
+  
 def initialize
 
 	@areas= {"GL"=> "G0" , "GR" => "G2"}
@@ -108,6 +110,7 @@ def initialize
 	@last_gl = "G0"
 	@single_shift = false
 end
+
 def reset 
 	@areas= {"GL"=> "G0" , "GR" => "G2"}
 	@sets = {"G0"=> "kanji1" , "G1" => "eisu", "G2"=>"hira","G3"=>"kata"}

data/lib/jis2euc/libjis2euc.rb

@@ -2,6 +2,7 @@
 # encoding: utf-8
 
 require 'iconv'
+require 'singleton'
 #require 'jis8ctl.rb'
 
 require File.join(File.dirname(__FILE__),'jis8ctl')
@@ -117,7 +118,7 @@ $katakana_to_euc = [
 	]
 
 
-$debug = false 
+$debug = true
 def verbose s
 	puts s if $debug 
 end
@@ -160,9 +161,12 @@ def test_display_eisu
 	puts eucjp_to_utf8(s_euc)
 end
 
-$jis8 = Jis8charset.new
-def arib_jis_to_euc s
+$jis8 = Jis8charset.instance
 
+
+def arib_jis_to_euc s , enable_debug = false
+
+  $debug = enable_debug
 	#convert string to array , so that we can index it freely
 	src = []
     out = ""

data/lib/jis2euc/version.rb

@@ -1,3 +1,3 @@
 module Jis2euc
-  VERSION = "0.0.1"
+  VERSION = "0.0.2"
 end

data/lib/test.rb

@@ -48,8 +48,35 @@ def test_euc_to_utf8
 end
 
 
+def test_verbose_output
+  
+   raw = @raw1
+   s = raw.split.map  {|t| ("0x"+t).to_i(16)}.inject("") {|p,c| p << c.chr} 
+   euc_s = Jis2euc.jis2euc(s,false)
+   print_out_euc euc_s
 end
 
+
+def test_print_convert_eucjp
+
+   raw = @raw3
+   s = raw.split.map  {|t| ("0x"+t).to_i(16)}.inject("") {|p,c| p << c.chr} 
+   euc_s = Jis2euc.jis2euc(s,false)
+
+   print_out_euc euc_s
+end
+
+
+def print_out_euc euc_s
+   puts "---------------------------------------------"
+   puts "view the characters in UTF-8 encoding console"
+   puts  Jis2euc.euc2utf8(euc_s)
+   puts "The EUC_JP encoding bytes :"
+   euc_s.each_byte {|c| print c.to_s(16) ; print ","}
+   puts "\n---------------------------------------------"
+end
+
+end
 #test_iconv_euc_to_utf8
 #test_display_eisu
 #test_arib_jis_to_euc_2

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: jis2euc
 version: !ruby/object:Gem::Version 
-  hash: 29
+  hash: 27
   prerelease: false
   segments: 
   - 0
   - 0
-  - 1
-  version: 0.0.1
+  - 2
+  version: 0.0.2
 platform: ruby
 authors: 
 - pierr.chen
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-07-05 00:00:00 +08:00
+date: 2011-08-26 00:00:00 +08:00
 default_executable: 
 dependencies: []
 
@@ -31,6 +31,7 @@ extra_rdoc_files: []
 files: 
 - .gitignore
 - Gemfile
+- README
 - Rakefile
 - jis2euc.gemspec
 - lib/jis2euc.rb