svnno****@sourc*****
svnno****@sourc*****
2009年 8月 17日 (月) 10:11:34 JST
Revision: 986
http://sourceforge.jp/projects/hiki/svn/view?view=rev&revision=986
Author: fdiary
Date: 2009-08-17 10:11:34 +0900 (Mon, 17 Aug 2009)
Log Message:
-----------
* hiki/docdiff/charstring.rb: code cleanup.
Modified Paths:
--------------
hiki/trunk/ChangeLog
hiki/trunk/hiki/config.rb
hiki/trunk/hiki/docdiff/charstring.rb
Modified: hiki/trunk/ChangeLog
===================================================================
--- hiki/trunk/ChangeLog 2009-08-16 17:46:38 UTC (rev 985)
+++ hiki/trunk/ChangeLog 2009-08-17 01:11:34 UTC (rev 986)
@@ -1,3 +1,6 @@
+2009-08-17 Kazuhiko <kazuh****@fdiar*****>
+ * hiki/docdiff/charstring.rb: code cleanup.
+
2009-08-16 Kazuhiko <kazuh****@fdiar*****>
* hiki/docdiff/charstring.rb: many changes for Ruby-1.9.
* hiki/docdiff/encoding/document.rb: do not guess encoding for
Modified: hiki/trunk/hiki/config.rb
===================================================================
--- hiki/trunk/hiki/config.rb 2009-08-16 17:46:38 UTC (rev 985)
+++ hiki/trunk/hiki/config.rb 2009-08-17 01:11:34 UTC (rev 986)
@@ -5,7 +5,7 @@
module Hiki
VERSION = '0.9dev'
- RELEASE_DATE = '2009-08-16'
+ RELEASE_DATE = '2009-08-17'
end
# For backward compatibility
Modified: hiki/trunk/hiki/docdiff/charstring.rb
===================================================================
--- hiki/trunk/hiki/docdiff/charstring.rb 2009-08-16 17:46:38 UTC (rev 985)
+++ hiki/trunk/hiki/docdiff/charstring.rb 2009-08-17 01:11:34 UTC (rev 986)
@@ -144,100 +144,100 @@
def split_to_char()
if eol_char # sometimes string has no end-of-line char
- encode('UTF-8').scan(Regexp.new("(?:#{eol_char})|(?:.)",
+ scan(Regexp.new("(?:#{eol_char})|(?:.)",
Regexp::MULTILINE)
- ).map{|e| e.encode(self.encoding)}
+ )
else # it seems that no EOL module was extended...
- encode('UTF-8').scan(Regexp.new("(?:.)",
+ scan(Regexp.new("(?:.)",
Regexp::MULTILINE)
- ).map{|e| e.encode(self.encoding)}
+ )
end
end
def count_latin_graph_char()
- encode('UTF-8').scan(Regexp.new("[#{Encodings['UTF-8']::GRAPH}]",
+ scan(Regexp.new("[#{Encodings['UTF-8']::GRAPH}]",
Regexp::MULTILINE)
).size
end
def count_ja_graph_char()
- encode('UTF-8').scan(Regexp.new("[#{Encodings['UTF-8']::JA_GRAPH}]",
+ scan(Regexp.new("[#{Encodings['UTF-8']::JA_GRAPH}]".encode(encoding),
Regexp::MULTILINE)
).size
end
def count_latin_blank_char()
- encode('UTF-8').scan(Regexp.new("[#{Encodings['UTF-8']::BLANK}]",
+ scan(Regexp.new("[#{Encodings['UTF-8']::BLANK}]",
Regexp::MULTILINE)
).size
end
def count_ja_blank_char()
- encode('UTF-8').scan(Regexp.new("[#{Encodings['UTF-8']::JA_BLANK}]",
+ scan(Regexp.new("[#{Encodings['UTF-8']::JA_BLANK}]".encode(encoding),
Regexp::MULTILINE)
).size
end
def split_to_word()
- encode('UTF-8').scan(Regexp.new(Encodings['UTF-8']::WORD_REGEXP_SRC,
+ scan(Regexp.new(Encodings['UTF-8']::WORD_REGEXP_SRC.encode(encoding),
Regexp::MULTILINE)
- ).map{|e| e.encode(self.encoding)}
+ )
end
def count_latin_word()
split_to_word.collect{|word|
word if Regexp.new("[#{Encodings['UTF-8']::PRINT}]",
- Regexp::MULTILINE).match word.encode('UTF-8')
+ Regexp::MULTILINE).match word
}.compact.size
end
def count_ja_word()
split_to_word.collect{|word|
- word if Regexp.new("[#{Encodings['UTF-8']::JA_PRINT}]",
- Regexp::MULTILINE).match word.encode('UTF-8')
+ word if Regexp.new("[#{Encodings['UTF-8']::JA_PRINT}]".encode(encoding),
+ Regexp::MULTILINE).match word
}.compact.size
end
def count_latin_valid_word()
split_to_word.collect{|word|
word if Regexp.new("[#{Encodings['UTF-8']::ALNUM}]",
- Regexp::MULTILINE).match word.encode('UTF-8')
+ Regexp::MULTILINE).match word
}.compact.size
end
def count_ja_valid_word()
split_to_word.collect{|word|
- word if Regexp.new("[#{Encodings['UTF-8']::JA_GRAPH}]",
- Regexp::MULTILINE).match word.encode('UTF-8')
+ word if Regexp.new("[#{Encodings['UTF-8']::JA_GRAPH}]".encode(encoding),
+ Regexp::MULTILINE).match word
}.compact.size
end
def split_to_line()
raise "EOLChars[eol] is #{EOLChars[eol].inspect}: eol not specified or auto-detection failed." unless EOLChars[eol]
if defined? eol_char
- encode('UTF-8').scan(Regexp.new(".*?#{eol_char}|.+",
+ scan(Regexp.new(".*?#{eol_char}|.+",
Regexp::MULTILINE)
- ).map{|e| e.encode(self.encoding)}
+ )
else
- encode('UTF-8').scan(Regexp.new(".+",
+ scan(Regexp.new(".+",
Regexp::MULTILINE)
- ).map{|e| e.encode(self.encoding)}
+ )
end
end
def count_graph_line()
split_to_line.collect{|line|
line if Regexp.new("[#{Encodings['UTF-8']::GRAPH}" +
- "#{Encodings['UTF-8']::JA_GRAPH}]",
- Regexp::MULTILINE).match line.encode('UTF-8')
+ "#{Encodings['UTF-8']::JA_GRAPH}]".encode(encoding),
+ Regexp::MULTILINE).match line
}.compact.size
end
def count_blank_line()
split_to_line.collect{|line|
line if Regexp.new("^[#{Encodings['UTF-8']::BLANK}" +
- "#{Encodings['UTF-8']::JA_BLANK}]+(?:#{eol_char})?",
- Regexp::MULTILINE).match line.encode('UTF-8')
+ "#{Encodings['UTF-8']::JA_BLANK}]+(?:#{eol_char})?".encode(encoding),
+ Regexp::MULTILINE).match line
}.compact.size
end