From ac4bee6fc338dc1533233c5f9467a0ce94ae91ab Mon Sep 17 00:00:00 2001 From: ser Date: Sun, 16 May 2004 15:19:22 +0000 Subject: Added support for CP-1252 and ISO-8859-15 encodings for non-iconv systems. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@6330 b2dd03c8-39d4-4d8f-98ff-823fe69b080e --- lib/rexml/encodings/ISO-8859-15.rb | 69 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 69 insertions(+) create mode 100644 lib/rexml/encodings/ISO-8859-15.rb (limited to 'lib/rexml/encodings/ISO-8859-15.rb') diff --git a/lib/rexml/encodings/ISO-8859-15.rb b/lib/rexml/encodings/ISO-8859-15.rb new file mode 100644 index 0000000000..ce565e7dd5 --- /dev/null +++ b/lib/rexml/encodings/ISO-8859-15.rb @@ -0,0 +1,69 @@ +# +# This class was contributed by Mikko Tiihonen mikko DOT tiihonen AT hut DOT fi +# +module REXML + module Encoding + @@__REXML_encoding_methods = %q~ + # Convert from UTF-8 + def to_iso_8859_15 content + array_utf8 = content.unpack('U*') + array_enc = [] + array_utf8.each do |num| + case num + # shortcut first bunch basic characters + when 0..0xA3: array_enc << num + # characters removed compared to iso-8859-1 + when 0xA4: array_enc << '¤' + when 0xA6: array_enc << '¦' + when 0xA8: array_enc << '¨' + when 0xB4: array_enc << '´' + when 0xB8: array_enc << '¸' + when 0xBC: array_enc << '¼' + when 0xBD: array_enc << '½' + when 0xBE: array_enc << '¾' + # characters added compared to iso-8859-1 + when 0x20AC: array_enc << 0xA4 # 0xe2 0x82 0xac + when 0x0160: array_enc << 0xA6 # 0xc5 0xa0 + when 0x0161: array_enc << 0xA8 # 0xc5 0xa1 + when 0x017D: array_enc << 0xB4 # 0xc5 0xbd + when 0x017E: array_enc << 0xB8 # 0xc5 0xbe + when 0x0152: array_enc << 0xBC # 0xc5 0x92 + when 0x0153: array_enc << 0xBD # 0xc5 0x93 + when 0x0178: array_enc << 0xBE # 0xc5 0xb8 + else + # all remaining basic characters can be used directly + if num <= 0xFF + array_enc << num + else + # Numeric entity (&#nnnn;); shard by Stefan Scholl + array_enc.concat "&\##{num};".unpack('C*') + end + end + end + array_enc.pack('C*') + end + + # Convert to UTF-8 + def from_iso_8859_15(str) + array_latin9 = str.unpack('C*') + array_enc = [] + array_latin9.each do |num| + case num + # characters that differ compared to iso-8859-1 + when 0xA4: array_enc << 0x20AC + when 0xA6: array_enc << 0x0160 + when 0xA8: array_enc << 0x0161 + when 0xB4: array_enc << 0x017D + when 0xB8: array_enc << 0x017E + when 0xBC: array_enc << 0x0152 + when 0xBD: array_enc << 0x0153 + when 0xBE: array_enc << 0x0178 + else + array_enc << num + end + end + array_enc.pack('U*') + end + ~ + end +end -- cgit v1.2.3