docdiff 0.6.1 → 0.6.4

data/test/docdiff_test.rb

@@ -1,10 +1,13 @@
 #!/usr/bin/ruby
 # -*- coding: us-ascii; -*-
+
+# frozen_string_literal: false
+
 require 'test/unit'
 require 'docdiff'
 require 'nkf'
 
-class TC_DocDiff_Document < Test::Unit::TestCase
+class TC_DocDiff < Test::Unit::TestCase
   Document = DocDiff::Document
 
   def setup()
@@ -126,7 +129,6 @@ class TC_DocDiff_Document < Test::Unit::TestCase
                "",
                nil].join
     expected = {:foo1=>true, :foo2=>"bar baz", :foo3=>123, :foo4=>false}
-    docdiff = DocDiff.new
     assert_equal(expected,
                  DocDiff.parse_config_file_content(content))
   end
@@ -188,7 +190,7 @@ class TC_DocDiff_Document < Test::Unit::TestCase
   def test_cli()
     expected = "Hello, my name is [-Watanabe.-]{+matz.+}\n"
     cmd = "ruby -I lib bin/docdiff --wdiff" +
-      " sample/01.en.ascii.lf sample/02.en.ascii.lf"
+      " test/fixture/01_en_ascii_lf.txt test/fixture/02_en_ascii_lf.txt"
     actual = `#{cmd}`.scan(/^.*?$\n/m).first
     assert_equal(expected, actual)
   end

data/test/document_test.rb

@@ -1,5 +1,8 @@
 #!/usr/bin/ruby
-# -*- coding: euc-jp; -*-
+# -*- coding: utf-8; -*-
+
+# frozen_string_literal: false
+
 require 'test/unit'
 require 'docdiff/document'
 require 'nkf'
@@ -220,396 +223,396 @@ class TC_DocDiff_Document < Test::Unit::TestCase
 
   # test EUCJP module
   def test_eucjp_split_to_word()
-    doc = Document.new(NKF.nkf("-e", "���ܸ��ʸ��foo bar"))
-    expected = ["���ܸ��","ʸ��","foo ","bar"].collect{|c| NKF.nkf("-e", c)}
+    doc = Document.new(NKF.nkf("--euc", "日本語の文字foo bar"))
+    expected = ["日本語の","文字","foo ","bar"].map{|c| NKF.nkf("--euc", c)}
     assert_equal(expected, doc.split_to_word)
   end
   def test_eucjp_split_to_word_kanhira()
-    doc = Document.new(NKF.nkf("-e", "���ܸ��ʸ��"))
-    expected = ["���ܸ��", "ʸ��"].collect{|c| NKF.nkf("-e", c)}
+    doc = Document.new(NKF.nkf("--euc", "日本語の文字"))
+    expected = ["日本語の", "文字"].map{|c| NKF.nkf("--euc", c)}
     assert_equal(expected, doc.split_to_word)
   end
   def test_eucjp_split_to_word_katahira()
-    doc = Document.new(NKF.nkf("-e", "�������ʤ�ʸ��"))
-    expected = ["�������ʤ�", "ʸ��"].collect{|c| NKF.nkf("-e", c)}
+    doc = Document.new(NKF.nkf("--euc", "カタカナの文字"))
+    expected = ["カタカナの", "文字"].map{|c| NKF.nkf("--euc", c)}
     assert_equal(expected, doc.split_to_word)
   end
   def test_eucjp_split_to_word_kataonbiki()
-    doc = Document.new(NKF.nkf("-e", "��ӡ�������"), "EUC-JP")
-    expected = ["��ӡ�", "����", "��"].collect{|c| NKF.nkf("-e", c)}
+    doc = Document.new(NKF.nkf("--euc", "ルビー色の石"), "EUC-JP")
+    expected = ["ルビー", "色の", "石"].map{|c| NKF.nkf("--euc", c)}
     assert_equal(expected, doc.split_to_word)
   end
   def test_eucjp_split_to_word_hiraonbiki()
-    doc = Document.new(NKF.nkf("-e", "���ӡ���"), "EUC-JP")
-    expected = (["�", "��ӡ���"]).collect{|c| NKF.nkf("-e", c)}
+    doc = Document.new(NKF.nkf("--euc", "わールビーだ"), "EUC-JP")
+    expected = (["わー", "ルビーだ"]).map{|c| NKF.nkf("--euc", c)}
     assert_equal(expected, doc.split_to_word)
   end
   def test_eucjp_split_to_word_latinmix()
-    doc = Document.new(NKF.nkf("-e", "���ܸ��Latin��ʸ��"))
-    expected = ["���ܸ��", "Latin", "��", "ʸ��"].collect{|c| NKF.nkf("-e", c)}
+    doc = Document.new(NKF.nkf("--euc", "日本語とLatinの文字"))
+    expected = ["日本語と", "Latin", "の", "文字"].map{|c| NKF.nkf("--euc", c)}
     assert_equal(expected, doc.split_to_word)
   end
   def test_eucjp_split_to_char()
-    doc = Document.new(NKF.nkf("-e", "���ܸ�a b"))
-    expected = ["��","��","��","a"," ","b"].collect{|c|NKF.nkf("-e",c)}
+    doc = Document.new(NKF.nkf("--euc", "日本語a b"))
+    expected = ["日","本","語","a"," ","b"].map{|c|NKF.nkf("--euc",c)}
     assert_equal(expected, doc.split_to_char)
   end
   def test_eucjp_split_to_char_with_cr()
-    doc = Document.new(NKF.nkf("-e", "���ܸ�a b\r"))
-    expected = ["��","��","��","a"," ","b","\r"].collect{|c|NKF.nkf("-e",c)}
+    doc = Document.new(NKF.nkf("--euc", "日本語a b\r"))
+    expected = ["日","本","語","a"," ","b","\r"].map{|c|NKF.nkf("--euc",c)}
     assert_equal(expected, doc.split_to_char)
   end
   def test_eucjp_split_to_char_with_lf()
-    doc = Document.new(NKF.nkf("-e", "���ܸ�a b\n"))
-    expected = ["��","��","��","a"," ","b","\n"].collect{|c|NKF.nkf("-e",c)}
+    doc = Document.new(NKF.nkf("--euc", "日本語a b\n"))
+    expected = ["日","本","語","a"," ","b","\n"].map{|c|NKF.nkf("--euc",c)}
     assert_equal(expected, doc.split_to_char)
   end
   def test_eucjp_split_to_char_with_crlf()
-    doc = Document.new(NKF.nkf("-e", "���ܸ�a b\r\n"))
-    expected = ["��","��","��","a"," ","b","\r\n"].collect{|c|NKF.nkf("-e",c)}
+    doc = Document.new(NKF.nkf("--euc", "日本語a b\r\n"))
+    expected = ["日","本","語","a"," ","b","\r\n"].map{|c|NKF.nkf("--euc",c)}
     assert_equal(expected, doc.split_to_char)
   end
   def test_eucjp_count_char()
-    doc = Document.new(NKF.nkf("-e", "���ܸ�a b\r\n"))
+    doc = Document.new(NKF.nkf("--euc", "日本語a b\r\n"))
     expected = 7
     assert_equal(expected, doc.count_char)
   end
   def test_eucjp_count_latin_graph_char()
-    doc = Document.new(NKF.nkf("-e", "���ܸ�a b\r\n"))
+    doc = Document.new(NKF.nkf("--euc", "日本語a b\r\n"))
     expected = 2
     assert_equal(expected, doc.count_latin_graph_char)
   end
   def test_eucjp_count_ja_graph_char()
-    doc = Document.new(NKF.nkf("-e", "���ܸ�a b\r\n"))
+    doc = Document.new(NKF.nkf("--euc", "日本語a b\r\n"))
     expected = 3
     assert_equal(expected, doc.count_ja_graph_char)
   end
   def test_eucjp_count_graph_char()
-    doc = Document.new(NKF.nkf("-e", "���ܸ�a b\r\n"))
+    doc = Document.new(NKF.nkf("--euc", "日本語a b\r\n"))
     expected = 5
     assert_equal(expected, doc.count_graph_char)
   end
   def test_eucjp_count_latin_blank_char()
-    doc = Document.new(NKF.nkf("-e", "���ܸ�\ta b\r\n"))
+    doc = Document.new(NKF.nkf("--euc", "日本語\ta b\r\n"))
     expected = 2
     assert_equal(expected, doc.count_latin_blank_char)
   end
   def test_eucjp_count_ja_blank_char()
-    doc = Document.new(NKF.nkf("-e", "���ܡ���\ta b\r\n"))
+    doc = Document.new(NKF.nkf("--euc", "日本　語\ta b\r\n"))
     expected = 1
     assert_equal(expected, doc.count_ja_blank_char)
   end
   def test_eucjp_count_blank_char()
-    doc = Document.new(NKF.nkf("-e", "���ܡ���\ta b\r\n"))
+    doc = Document.new(NKF.nkf("--euc", "日本　語\ta b\r\n"))
     expected = 3
     assert_equal(expected, doc.count_blank_char)
   end
   def test_eucjp_count_word()
-    doc = Document.new(NKF.nkf("-e", "���ܡ���a b --\r\n"))
+    doc = Document.new(NKF.nkf("--euc", "日本　語a b --\r\n"))
     expected = 7 # "--" and "\r\n" are counted as word here (though not "valid")
     assert_equal(expected, doc.count_word)
   end
   def test_eucjp_count_ja_word()
-    doc = Document.new(NKF.nkf("-e", "���ܡ���a b --\r\n"))
+    doc = Document.new(NKF.nkf("--euc", "日本　語a b --\r\n"))
     expected = 3
     assert_equal(expected, doc.count_ja_word)
   end
   def test_eucjp_count_latin_valid_word()
-    doc = Document.new(NKF.nkf("-e", "���ܡ���a b --\r\n"))
+    doc = Document.new(NKF.nkf("--euc", "日本　語a b --\r\n"))
     expected = 2
     assert_equal(expected, doc.count_latin_valid_word)
   end
   def test_eucjp_count_ja_valid_word()
-    doc = Document.new(NKF.nkf("-e", "���ܡ���a b --\r\n"))
+    doc = Document.new(NKF.nkf("--euc", "日本　語a b --\r\n"))
     expected = 2
     assert_equal(expected, doc.count_ja_valid_word)
   end
   def test_eucjp_count_valid_word()
-    doc = Document.new(NKF.nkf("-e", "���ܡ���a b --\r\n"))
+    doc = Document.new(NKF.nkf("--euc", "日本　語a b --\r\n"))
     expected = 4
     assert_equal(expected, doc.count_valid_word)
   end
   def test_eucjp_count_line()
-    doc = Document.new(NKF.nkf("-e", "���ܸ�\r\n��\r\n \r\n\r\nfoo\r\nbar"))
+    doc = Document.new(NKF.nkf("--euc", "日本語\r\n　\r\n \r\n\r\nfoo\r\nbar"))
     expected = 6
     assert_equal(expected, doc.count_line)
   end
   def test_eucjp_count_graph_line()
-    doc = Document.new(NKF.nkf("-e", "���ܸ�\r\n��\r\n \r\n\r\nfoo\r\nbar"))
+    doc = Document.new(NKF.nkf("--euc", "日本語\r\n　\r\n \r\n\r\nfoo\r\nbar"))
     expected = 3
     assert_equal(expected, doc.count_graph_line)
   end
   def test_eucjp_count_empty_line()
-    doc = Document.new(NKF.nkf("-e", "���ܸ�\r\n��\r\n \r\n\r\nfoo\r\nbar"))
+    doc = Document.new(NKF.nkf("--euc", "日本語\r\n　\r\n \r\n\r\nfoo\r\nbar"))
     expected = 1
     assert_equal(expected, doc.count_empty_line)
   end
   def test_eucjp_count_blank_line()
-    doc = Document.new(NKF.nkf("-e", "���ܸ�\r\n��\r\n \r\n\r\nfoo\r\nbar"))
+    doc = Document.new(NKF.nkf("--euc", "日本語\r\n　\r\n \r\n\r\nfoo\r\nbar"))
     expected = 2
     assert_equal(expected, doc.count_blank_line)
   end
 
   # test SJIS module
   def test_sjis_split_to_word()
-    doc = Document.new(NKF.nkf("-s", "���ܸ��ʸ��foo bar"))
-    expected = ["���ܸ��", "ʸ��", "foo ", "bar"].collect{|c|NKF.nkf("-s",c)}
+    doc = Document.new(NKF.nkf("--sjis", "日本語の文字foo bar"))
+    expected = ["日本語の", "文字", "foo ", "bar"].map{|c|NKF.nkf("--sjis",c)}
     assert_equal(expected, doc.split_to_word)
   end
   def test_sjisplit_s_to_word_kanhira()
-    doc = Document.new(NKF.nkf("-s", "���ܸ��ʸ��"))
-    expected = ["���ܸ��", "ʸ��"].collect{|c| NKF.nkf("-s", c)}
+    doc = Document.new(NKF.nkf("--sjis", "日本語の文字"))
+    expected = ["日本語の", "文字"].map{|c| NKF.nkf("--sjis", c)}
     assert_equal(expected, doc.split_to_word)
   end
   def test_sjis_split_to_word_katahira()
-    doc = Document.new(NKF.nkf("-s", "�������ʤ�ʸ��"))
-    expected = ["�������ʤ�", "ʸ��"].collect{|c| NKF.nkf("-s", c)}
+    doc = Document.new(NKF.nkf("--sjis", "カタカナの文字"))
+    expected = ["カタカナの", "文字"].map{|c| NKF.nkf("--sjis", c)}
     assert_equal(expected, doc.split_to_word)
   end
   def test_sjis_split_to_word_kataonbiki()
-    doc = Document.new(NKF.nkf("-s", "��ӡ��λ���"))
-    expected = ["��ӡ���", "����"].collect{|c| NKF.nkf("-s", c)}
+    doc = Document.new(NKF.nkf("--sjis", "ルビーの指輪"))
+    expected = ["ルビーの", "指輪"].map{|c| NKF.nkf("--sjis", c)}
     assert_equal(expected, doc.split_to_word)
   end
   def test_sjis_split_to_word_hiraonbiki()
-    doc = Document.new(NKF.nkf("-s", "���ӡ���"))
-    expected = ["�", "��ӡ���"].collect{|c| NKF.nkf("-s", c)}
+    doc = Document.new(NKF.nkf("--sjis", "わールビーだ"))
+    expected = ["わー", "ルビーだ"].map{|c| NKF.nkf("--sjis", c)}
     assert_equal(expected, doc.split_to_word)
   end
   def test_sjis_split_to_word_latinmix()
-    doc = Document.new(NKF.nkf("-s", "���ܸ��Latin��ʸ��"))
-    expected = ["���ܸ��","Latin","��","ʸ��"].collect{|c| NKF.nkf("-s", c)}
+    doc = Document.new(NKF.nkf("--sjis", "日本語とLatinの文字"))
+    expected = ["日本語と","Latin","の","文字"].map{|c| NKF.nkf("--sjis", c)}
     assert_equal(expected, doc.split_to_word)
   end
   def test_sjis_split_to_char()
-    doc = Document.new(NKF.nkf("-s", "ɽ�׻�a b"))
-    expected = ["ɽ","��","��","a"," ","b"].collect{|c|NKF.nkf("-s",c)}
+    doc = Document.new(NKF.nkf("--sjis", "表計算a b"))
+    expected = ["表","計","算","a"," ","b"].map{|c|NKF.nkf("--sjis",c)}
     assert_equal(expected, doc.split_to_char)
   end
   def test_sjis_split_to_char_with_cr()
-    doc = Document.new(NKF.nkf("-s", "ɽ�׻�a b\r"))
-    expected = ["ɽ","��","��","a"," ","b","\r"].collect{|c|NKF.nkf("-s",c)}
+    doc = Document.new(NKF.nkf("--sjis", "表計算a b\r"))
+    expected = ["表","計","算","a"," ","b","\r"].map{|c|NKF.nkf("--sjis",c)}
     assert_equal(expected, doc.split_to_char)
   end
   def test_sjis_split_to_char_with_lf()
-    doc = Document.new(NKF.nkf("-s", "ɽ�׻�a b\n"))
-    expected = ["ɽ","��","��","a"," ","b","\n"].collect{|c|NKF.nkf("-s",c)}
+    doc = Document.new(NKF.nkf("--sjis", "表計算a b\n"))
+    expected = ["表","計","算","a"," ","b","\n"].map{|c|NKF.nkf("--sjis",c)}
     assert_equal(expected, doc.split_to_char)
   end
   def test_sjis_split_to_char_with_crlf()
-    doc = Document.new(NKF.nkf("-s", "ɽ�׻�a b\r\n"))
-    expected = ["ɽ","��","��","a"," ","b","\r\n"].collect{|c|NKF.nkf("-s",c)}
+    doc = Document.new(NKF.nkf("--sjis", "表計算a b\r\n"))
+    expected = ["表","計","算","a"," ","b","\r\n"].map{|c|NKF.nkf("--sjis",c)}
     assert_equal(expected, doc.split_to_char)
   end
   def test_sjis_count_char()
-    doc = Document.new(NKF.nkf("-s", "���ܸ�a b\r\n"))
+    doc = Document.new(NKF.nkf("--sjis", "日本語a b\r\n"))
     expected = 7
     assert_equal(expected, doc.count_char)
   end
   def test_sjis_count_latin_graph_char()
-    doc = Document.new(NKF.nkf("-s", "���ܸ�a b\r\n"))
+    doc = Document.new(NKF.nkf("--sjis", "日本語a b\r\n"))
     expected = 2
     assert_equal(expected, doc.count_latin_graph_char)
   end
   def test_sjis_count_ja_graph_char()
-    doc = Document.new(NKF.nkf("-s", "���ܸ�a b\r\n"))
+    doc = Document.new(NKF.nkf("--sjis", "日本語a b\r\n"))
     expected = 3
     assert_equal(expected, doc.count_ja_graph_char)
   end
   def test_sjis_count_graph_char()
-    doc = Document.new(NKF.nkf("-s", "���ܸ�a b\r\n"))
+    doc = Document.new(NKF.nkf("--sjis", "日本語a b\r\n"))
     expected = 5
     assert_equal(expected, doc.count_graph_char)
   end
   def test_sjis_count_latin_blank_char()
-    doc = Document.new(NKF.nkf("-s", "���ܸ�\ta b\r\n"))
+    doc = Document.new(NKF.nkf("--sjis", "日本語\ta b\r\n"))
     expected = 2
     assert_equal(expected, doc.count_latin_blank_char)
   end
   def test_sjis_count_ja_blank_char()
-    doc = Document.new(NKF.nkf("-s", "���ܡ���\ta b\r\n"))
+    doc = Document.new(NKF.nkf("--sjis", "日本　語\ta b\r\n"))
     expected = 1
     assert_equal(expected, doc.count_ja_blank_char)
   end
   def test_sjis_count_blank_char()
-    doc = Document.new(NKF.nkf("-s", "���ܡ���\ta b\r\n"))
+    doc = Document.new(NKF.nkf("--sjis", "日本　語\ta b\r\n"))
     expected = 3
     assert_equal(expected, doc.count_blank_char)
   end
   def test_sjis_count_word()
-    doc = Document.new(NKF.nkf("-s", "���ܡ���a b --\r\n"))
+    doc = Document.new(NKF.nkf("--sjis", "日本　語a b --\r\n"))
     expected = 7 # "--" and "\r\n" are counted as word here (though not "valid")
     assert_equal(expected, doc.count_word)
   end
   def test_sjis_count_ja_word()
-    doc = Document.new(NKF.nkf("-s", "���ܡ���a b --\r\n"))
+    doc = Document.new(NKF.nkf("--sjis", "日本　語a b --\r\n"))
     expected = 3
     assert_equal(expected, doc.count_ja_word)
   end
   def test_sjis_count_latin_valid_word()
-    doc = Document.new(NKF.nkf("-s", "���ܡ���a b --\r\n"))
+    doc = Document.new(NKF.nkf("--sjis", "日本　語a b --\r\n"))
     expected = 2
     assert_equal(expected, doc.count_latin_valid_word)
   end
   def test_sjis_count_ja_valid_word()
-    doc = Document.new(NKF.nkf("-s", "���ܡ���a b --\r\n"))
+    doc = Document.new(NKF.nkf("--sjis", "日本　語a b --\r\n"))
     expected = 2
     assert_equal(expected, doc.count_ja_valid_word)
   end
   def test_sjis_count_valid_word()
-    doc = Document.new(NKF.nkf("-s", "���ܡ���a b --\r\n"))
+    doc = Document.new(NKF.nkf("--sjis", "日本　語a b --\r\n"))
     expected = 4
     assert_equal(expected, doc.count_valid_word)
   end
   def test_sjis_count_line()
-    doc = Document.new(NKF.nkf("-s", "���ܸ�\r\n��\r\n \r\n\r\nfoo\r\nbar"))
+    doc = Document.new(NKF.nkf("--sjis", "日本語\r\n　\r\n \r\n\r\nfoo\r\nbar"))
     expected = 6
     assert_equal(expected, doc.count_line)
   end
   def test_sjis_count_graph_line()
-    doc = Document.new(NKF.nkf("-s", "���ܸ�\r\n��\r\n \r\n\r\nfoo\r\nbar"))
+    doc = Document.new(NKF.nkf("--sjis", "日本語\r\n　\r\n \r\n\r\nfoo\r\nbar"))
     expected = 3
     assert_equal(expected, doc.count_graph_line)
   end
   def test_sjis_count_empty_line()
-    doc = Document.new(NKF.nkf("-s", "���ܸ�\r\n��\r\n \r\n\r\nfoo\r\nbar"))
+    doc = Document.new(NKF.nkf("--sjis", "日本語\r\n　\r\n \r\n\r\nfoo\r\nbar"))
     expected = 1
     assert_equal(expected, doc.count_empty_line)
   end
   def test_sjis_count_blank_line()
-    doc = Document.new(NKF.nkf("-s", "���ܸ�\r\n��\r\n \r\n\r\nfoo\r\nbar"))
+    doc = Document.new(NKF.nkf("--sjis", "日本語\r\n　\r\n \r\n\r\nfoo\r\nbar"))
     expected = 2
     assert_equal(expected, doc.count_blank_line)
   end
 
   # test UTF8 module
   def test_utf8_split_to_word()
-    doc = Document.new(NKF.nkf("-E -w", "���ܸ��ʸ��foo bar"))
-    expected = ["���ܸ��", "ʸ��", "foo ", "bar"].collect{|c| NKF.nkf("-E -w", c)}
+    doc = Document.new(NKF.nkf("--utf8", "日本語の文字foo bar"))
+    expected = ["日本語の", "文字", "foo ", "bar"].map{|c| NKF.nkf("--utf8", c)}
     assert_equal(expected, doc.split_to_word)
   end
   def test_utf8_split_to_word_kanhira()
-    doc = Document.new(NKF.nkf("-E -w", "���ܸ��ʸ��"))
-    expected = ["���ܸ��", "ʸ��"].collect{|c| NKF.nkf("-E -w", c)}
+    doc = Document.new(NKF.nkf("--utf8", "日本語の文字"))
+    expected = ["日本語の", "文字"].map{|c| NKF.nkf("--utf8", c)}
     assert_equal(expected, doc.split_to_word)
   end
   def test_utf8_split_to_word_katahira()
-    doc = Document.new(NKF.nkf("-E -w", "�������ʤ�ʸ��"))
-    expected = ["�������ʤ�", "ʸ��"].collect{|c| NKF.nkf("-E -w", c)}
+    doc = Document.new(NKF.nkf("--utf8", "カタカナの文字"))
+    expected = ["カタカナの", "文字"].map{|c| NKF.nkf("--utf8", c)}
     assert_equal(expected, doc.split_to_word)
   end
   def test_utf8_split_to_word_kataonbiki()
-    doc = Document.new(NKF.nkf("-E -w", "��ӡ��λ���"))
-    expected = ["��ӡ���", "����"].collect{|c| NKF.nkf("-E -w", c)}
+    doc = Document.new(NKF.nkf("--utf8", "ルビーの指輪"))
+    expected = ["ルビーの", "指輪"].map{|c| NKF.nkf("--utf8", c)}
     assert_equal(expected, doc.split_to_word)
   end
   def test_utf8_split_to_word_hiraonbiki()
-    doc = Document.new(NKF.nkf("-E -w", "���ӡ���"))
-    expected = ["�", "��ӡ���"].collect{|c| NKF.nkf("-E -w", c)}
+    doc = Document.new(NKF.nkf("--utf8", "わールビーだ"))
+    expected = ["わー", "ルビーだ"].map{|c| NKF.nkf("--utf8", c)}
     assert_equal(expected, doc.split_to_word)
   end
   def test_utf8_split_to_word_latinmix()
-    doc = Document.new(NKF.nkf("-E -w", "���ܸ��Latin��ʸ��"))
-    expected = ["���ܸ��", "Latin", "��", "ʸ��"].collect{|c| NKF.nkf("-E -w", c)}
+    doc = Document.new(NKF.nkf("--utf8", "日本語とLatinの文字"))
+    expected = ["日本語と", "Latin", "の", "文字"].map{|c| NKF.nkf("--utf8", c)}
     assert_equal(expected, doc.split_to_word)
   end
   def test_utf8_split_to_char()
-    doc = Document.new(NKF.nkf("-E -w", "���ܸ�a b"), "UTF-8")
-    expected = ["��", "��", "��", "a", " ", "b"].collect{|c| NKF.nkf("-E -w", c)}
+    doc = Document.new(NKF.nkf("--utf8", "日本語a b"), "UTF-8")
+    expected = ["日", "本", "語", "a", " ", "b"].map{|c| NKF.nkf("--utf8", c)}
     assert_equal(expected, doc.split_to_char)
   end
   def test_utf8_split_to_char_with_cr()
-    doc = Document.new(NKF.nkf("-E -w", "���ܸ�a b\r"), "UTF-8")
-    expected = ["��","��","��","a"," ","b","\r"].collect{|c| NKF.nkf("-E -w", c)}
+    doc = Document.new(NKF.nkf("--utf8", "日本語a b\r"), "UTF-8")
+    expected = ["日","本","語","a"," ","b","\r"].map{|c| NKF.nkf("--utf8", c)}
     assert_equal(expected, doc.split_to_char)
   end
   def test_utf8_split_to_char_with_lf()
-    doc = Document.new(NKF.nkf("-E -w", "���ܸ�a b\n"), "UTF-8")
-    expected = ["��","��","��","a"," ","b","\n"].collect{|c| NKF.nkf("-E -w", c)}
+    doc = Document.new(NKF.nkf("--utf8", "日本語a b\n"), "UTF-8")
+    expected = ["日","本","語","a"," ","b","\n"].map{|c| NKF.nkf("--utf8", c)}
     assert_equal(expected, doc.split_to_char)
   end
   def test_utf8_split_to_char_with_crlf()
-    doc = Document.new(NKF.nkf("-E -w", "���ܸ�a b\r\n"), "UTF-8")
-    expected = ["��","��","��","a"," ","b","\r\n"].collect{|c| NKF.nkf("-E -w", c)}
+    doc = Document.new(NKF.nkf("--utf8", "日本語a b\r\n"), "UTF-8")
+    expected = ["日","本","語","a"," ","b","\r\n"].map{|c| NKF.nkf("--utf8", c)}
     assert_equal(expected, doc.split_to_char)
   end
   def test_utf8_count_char()
-    doc = Document.new(NKF.nkf("-E -w", "���ܸ�a b\r\n"), "UTF-8")
+    doc = Document.new(NKF.nkf("--utf8", "日本語a b\r\n"), "UTF-8")
     expected = 7
     assert_equal(expected, doc.count_char)
   end
   def test_utf8_count_latin_graph_char()
-    doc = Document.new(NKF.nkf("-E -w", "���ܸ�a b\r\n"), "UTF-8")
+    doc = Document.new(NKF.nkf("--utf8", "日本語a b\r\n"), "UTF-8")
     expected = 2
     assert_equal(expected, doc.count_latin_graph_char)
   end
   def test_utf8_count_ja_graph_char()
-    doc = Document.new(NKF.nkf("-E -w", "���ܸ�a b\r\n"), "UTF-8")
+    doc = Document.new(NKF.nkf("--utf8", "日本語a b\r\n"), "UTF-8")
     expected = 3
     assert_equal(expected, doc.count_ja_graph_char)
   end
   def test_utf8_count_graph_char()
-    doc = Document.new(NKF.nkf("-E -w", "���ܸ�a b\r\n"), "UTF-8")
+    doc = Document.new(NKF.nkf("--utf8", "日本語a b\r\n"), "UTF-8")
     expected = 5
     assert_equal(expected, doc.count_graph_char)
   end
   def test_utf8_count_latin_blank_char()
-    doc = Document.new(NKF.nkf("-E -w", "���ܸ�\ta b\r\n"))
+    doc = Document.new(NKF.nkf("--utf8", "日本語\ta b\r\n"))
     expected = 2
     assert_equal(expected, doc.count_latin_blank_char)
   end
   def test_utf8_count_ja_blank_char()
-    doc = Document.new(NKF.nkf("-E -w", "���ܡ���\ta b\r\n"))
+    doc = Document.new(NKF.nkf("--utf8", "日本　語\ta b\r\n"))
     expected = 1
     assert_equal(expected, doc.count_ja_blank_char)
   end
   def test_utf8_count_blank_char()
-    doc = Document.new(NKF.nkf("-E -w", "���ܡ���\ta b\r\n"))
+    doc = Document.new(NKF.nkf("--utf8", "日本　語\ta b\r\n"))
     expected = 3
     assert_equal(expected, doc.count_blank_char)
   end
   def test_utf8_count_word()
-    doc = Document.new(NKF.nkf("-E -w", "���ܡ���a b --\r\n"))
+    doc = Document.new(NKF.nkf("--utf8", "日本　語a b --\r\n"))
     expected = 7 # "--" and "\r\n" are counted as word here (though not "valid")
     assert_equal(expected, doc.count_word)
   end
   def test_utf8_count_ja_word()
-    doc = Document.new(NKF.nkf("-E -w", "���ܡ���a b --\r\n"))
+    doc = Document.new(NKF.nkf("--utf8", "日本　語a b --\r\n"))
     expected = 3
     assert_equal(expected, doc.count_ja_word)
   end
   def test_utf8_count_latin_valid_word()
-    doc = Document.new(NKF.nkf("-E -w", "���ܡ���a b --\r\n"))
+    doc = Document.new(NKF.nkf("--utf8", "日本　語a b --\r\n"))
     expected = 2
     assert_equal(expected, doc.count_latin_valid_word)
   end
   def test_utf8_count_ja_valid_word()
-    doc = Document.new(NKF.nkf("-E -w", "���ܡ���a b --\r\n"))
+    doc = Document.new(NKF.nkf("--utf8", "日本　語a b --\r\n"))
     expected = 2
     assert_equal(expected, doc.count_ja_valid_word)
   end
   def test_utf8_count_valid_word()
-    doc = Document.new(NKF.nkf("-E -w", "���ܡ���a b --\r\n"))
+    doc = Document.new(NKF.nkf("--utf8", "日本　語a b --\r\n"))
     expected = 4
     assert_equal(expected, doc.count_valid_word)
   end
   def test_utf8_count_line()
-    doc = Document.new(NKF.nkf("-E -w", "���ܸ�\r\n��\r\n \r\n\r\nfoo\r\nbar"))
+    doc = Document.new(NKF.nkf("--utf8", "日本語\r\n　\r\n \r\n\r\nfoo\r\nbar"))
     expected = 6
     assert_equal(expected, doc.count_line)
   end
   def test_utf8_count_graph_line()
-    doc = Document.new(NKF.nkf("-E -w", "���ܸ�\r\n��\r\n \r\n\r\nfoo\r\nbar"))
+    doc = Document.new(NKF.nkf("--utf8", "日本語\r\n　\r\n \r\n\r\nfoo\r\nbar"))
     expected = 3
     assert_equal(expected, doc.count_graph_line)
   end
   def test_utf8_count_empty_line()
-    doc = Document.new(NKF.nkf("-E -w", "���ܸ�\r\n��\r\n \r\n\r\nfoo\r\nbar"))
+    doc = Document.new(NKF.nkf("--utf8", "日本語\r\n　\r\n \r\n\r\nfoo\r\nbar"))
     expected = 1
     assert_equal(expected, doc.count_empty_line)
   end
   def test_utf8_count_blank_line()
-    doc = Document.new(NKF.nkf("-E -w", "���ܸ�\r\n��\r\n \r\n\r\nfoo\r\nbar"))
+    doc = Document.new(NKF.nkf("--utf8", "日本語\r\n　\r\n \r\n\r\nfoo\r\nbar"))
     expected = 2
     assert_equal(expected, doc.count_blank_line)
   end

data/test/fixture/01_ja_utf8_lf.txt

@@ -0,0 +1,2 @@
+こんにちは、私の名前はわたなべです。
+私はJust Another Ruby Porterです。

data/test/fixture/02_ja_utf8_lf.txt

@@ -0,0 +1,2 @@
+こんばんは、私の名前はまつもとです。
+Rubyを作ったのは私です。私はRuby Hackerです。