1berry/ruby
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

* forgot to add this file in the previous commit.

Browse Source 
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@4615 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This commit is contained in:
nahi 2003-09-28 09:33:59 +00:00
parent d57fc5a489
commit eb8ee5e401
1 changed files with 11 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
lib/xsd/charset.rb
View File

@ -117,12 +117,13 @@ public
CharsetMap.index(label.downcase) CharsetMap.index(label.downcase)
end end
# Original regexps: http://www.din.or.jp/~ohzaki/perl.htm # us_ascii = '[\x00-\x7F]'
# ascii_euc = '[\x00-\x7F]' us_ascii = '[\x9\xa\xd\x20-\x7F]' # XML 1.0 restricted.
ascii_euc = '[\x9\xa\xd\x20-\x7F]' # XML 1.0 restricted. USASCIIRegexp = Regexp.new("\\A#{ us_ascii }*\\z", nil, "NONE")
twobytes_euc = '(?:[\x8E\xA1-\xFE][\xA1-\xFE])' twobytes_euc = '(?:[\x8E\xA1-\xFE][\xA1-\xFE])'
threebytes_euc = '(?:\x8F[\xA1-\xFE][\xA1-\xFE])' threebytes_euc = '(?:\x8F[\xA1-\xFE][\xA1-\xFE])'
character_euc = "(?:#{ ascii_euc }|#{ twobytes_euc }|#{ threebytes_euc })" character_euc = "(?:#{ us_ascii }|#{ twobytes_euc }|#{ threebytes_euc })"
EUCRegexp = Regexp.new("\\A#{ character_euc }*\\z", nil, "NONE") EUCRegexp = Regexp.new("\\A#{ character_euc }*\\z", nil, "NONE")
# onebyte_sjis = '[\x00-\x7F\xA1-\xDF]' # onebyte_sjis = '[\x00-\x7F\xA1-\xDF]'
@ -132,17 +133,19 @@ public
SJISRegexp = Regexp.new("\\A#{ character_sjis }*\\z", nil, "NONE") SJISRegexp = Regexp.new("\\A#{ character_sjis }*\\z", nil, "NONE")
# 0xxxxxxx # 0xxxxxxx
#ascii_utf8 = '[\0-\x7F]'
ascii_utf8 = '[\x9\xA\xD\x20-\x7F]' # XML 1.0 restricted.
# 110yyyyy 10xxxxxx # 110yyyyy 10xxxxxx
twobytes_utf8 = '(?:[\xC0-\xDF][\x80-\xBF])' twobytes_utf8 = '(?:[\xC0-\xDF][\x80-\xBF])'
# 1110zzzz 10yyyyyy 10xxxxxx # 1110zzzz 10yyyyyy 10xxxxxx
threebytes_utf8 = '(?:[\xE0-\xEF][\x80-\xBF][\x80-\xBF])' threebytes_utf8 = '(?:[\xE0-\xEF][\x80-\xBF][\x80-\xBF])'
# 11110uuu 10uuuzzz 10yyyyyy 10xxxxxx # 11110uuu 10uuuzzz 10yyyyyy 10xxxxxx
fourbytes_utf8 = '(?:[\xF0-\xF7][\x80-\xBF][\x80-\xBF][\x80-\xBF])' fourbytes_utf8 = '(?:[\xF0-\xF7][\x80-\xBF][\x80-\xBF][\x80-\xBF])'
character_utf8 = "(?:#{ ascii_utf8 }|#{ twobytes_utf8 }|#{ threebytes_utf8 }|#{ fourbytes_utf8 })" character_utf8 = "(?:#{ us_ascii }|#{ twobytes_utf8 }|#{ threebytes_utf8 }|#{ fourbytes_utf8 })"
UTF8Regexp = Regexp.new("\\A#{ character_utf8 }*\\z", nil, "NONE") UTF8Regexp = Regexp.new("\\A#{ character_utf8 }*\\z", nil, "NONE")
def Charset.is_us_ascii(str)
USASCIIRegexp =~ str
end
def Charset.is_utf8(str) def Charset.is_utf8(str)
UTF8Regexp =~ str UTF8Regexp =~ str
end end
@ -158,7 +161,7 @@ public
def Charset.is_ces(str, code = $KCODE) def Charset.is_ces(str, code = $KCODE)
case code case code
when 'NONE' when 'NONE'
true is_us_ascii(str)
when 'UTF8' when 'UTF8'
is_utf8(str) is_utf8(str)
when 'EUC' when 'EUC'