ruby--ruby/lib/rexml/encodings/ISO-8859-15.rb

73 lines
2.3 KiB
Ruby
Raw Normal View History

#
# This class was contributed by Mikko Tiihonen mikko DOT tiihonen AT hut DOT fi
#
module REXML
module Encoding
Merges upstream changes for REXML v3.1.7 http://www.germane-software.com/repos/rexml/tags/3.1.7 r1278@bean: ser | 2007-06-07 00:53:06 -0400 Fixed a double-encoding bug. This was a regression, related to ticket:48. r1292@bean: ser | 2007-07-25 08:19:36 -0400 r1279@bean: ser | 2007-06-09 23:19:02 -0400 Fixes ticket:89 -- encoding CP-1252 was broken. ISO-8859-15 had the same problem. Also in this patch is a fix to merge.rb (unused, but it should at least contain no errors), and a unit test for ticket:88. r1293@bean: ser | 2007-07-25 08:19:37 -0400 r1281@bean: ser | 2007-07-24 11:08:48 -0400 Addresses ticket:85 This is a major rewrite of the XML formatting code. The XML writers have all been extracted out of the classes and put into their own class containers. This makes writing parsers easier, and cleaner. There are three formatters, which correspond to the previous three XML writing modes: REXML::Formatters::Default Prints the XML document exactly as it was parsed REXML::Formatters::Pretty Pretty prints the XML document, destroying whitespace in the document REXML::Formatters::Transitive Pretty prints the XML document, preserving whitespace All of the write() functions have been deprecated (some are still used, but these will also go away) except the write() function on Document, which is left for convenience. To pretty print an XML document the canonical way: formatter = REXML::Formatters::Pretty.new( 5 ) # indent by 5 spaces formatter.write( document, output ) r1294@bean: ser | 2007-07-25 08:19:38 -0400 r1283@bean: ser | 2007-07-24 19:53:30 -0400 This goes with the previous commit. r1295@bean: ser | 2007-07-25 08:19:39 -0400 r1285@bean: ser | 2007-07-24 20:02:07 -0400 And THIS goes with the previous two patches. Dammit. r1296@bean: ser | 2007-07-25 08:19:40 -0400 r1287@bean: ser | 2007-07-24 20:12:25 -0400 Applied patch from Jeff Barczewski. Note that this changes what the values of the name and IDs are from the previous behavior -- the values no longer include the quotes. This is the correct behavior, so I'm leaving it in, but it is not backwards compatible. Also fixes the serializer so that it outputs the doctype in a correct format (needed as a result of this change). r1297@bean: ser | 2007-07-25 08:38:38 -0400 Version update git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@12844 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2007-07-25 12:47:23 +00:00
register("ISO-8859-15") do |o|
alias encode to_iso_8859_15
alias decode from_iso_8859_15
Merges upstream changes for REXML v3.1.7 http://www.germane-software.com/repos/rexml/tags/3.1.7 r1278@bean: ser | 2007-06-07 00:53:06 -0400 Fixed a double-encoding bug. This was a regression, related to ticket:48. r1292@bean: ser | 2007-07-25 08:19:36 -0400 r1279@bean: ser | 2007-06-09 23:19:02 -0400 Fixes ticket:89 -- encoding CP-1252 was broken. ISO-8859-15 had the same problem. Also in this patch is a fix to merge.rb (unused, but it should at least contain no errors), and a unit test for ticket:88. r1293@bean: ser | 2007-07-25 08:19:37 -0400 r1281@bean: ser | 2007-07-24 11:08:48 -0400 Addresses ticket:85 This is a major rewrite of the XML formatting code. The XML writers have all been extracted out of the classes and put into their own class containers. This makes writing parsers easier, and cleaner. There are three formatters, which correspond to the previous three XML writing modes: REXML::Formatters::Default Prints the XML document exactly as it was parsed REXML::Formatters::Pretty Pretty prints the XML document, destroying whitespace in the document REXML::Formatters::Transitive Pretty prints the XML document, preserving whitespace All of the write() functions have been deprecated (some are still used, but these will also go away) except the write() function on Document, which is left for convenience. To pretty print an XML document the canonical way: formatter = REXML::Formatters::Pretty.new( 5 ) # indent by 5 spaces formatter.write( document, output ) r1294@bean: ser | 2007-07-25 08:19:38 -0400 r1283@bean: ser | 2007-07-24 19:53:30 -0400 This goes with the previous commit. r1295@bean: ser | 2007-07-25 08:19:39 -0400 r1285@bean: ser | 2007-07-24 20:02:07 -0400 And THIS goes with the previous two patches. Dammit. r1296@bean: ser | 2007-07-25 08:19:40 -0400 r1287@bean: ser | 2007-07-24 20:12:25 -0400 Applied patch from Jeff Barczewski. Note that this changes what the values of the name and IDs are from the previous behavior -- the values no longer include the quotes. This is the correct behavior, so I'm leaving it in, but it is not backwards compatible. Also fixes the serializer so that it outputs the doctype in a correct format (needed as a result of this change). r1297@bean: ser | 2007-07-25 08:38:38 -0400 Version update git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@12844 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2007-07-25 12:47:23 +00:00
end
# Convert from UTF-8
Merges upstream changes for REXML v3.1.7 http://www.germane-software.com/repos/rexml/tags/3.1.7 r1278@bean: ser | 2007-06-07 00:53:06 -0400 Fixed a double-encoding bug. This was a regression, related to ticket:48. r1292@bean: ser | 2007-07-25 08:19:36 -0400 r1279@bean: ser | 2007-06-09 23:19:02 -0400 Fixes ticket:89 -- encoding CP-1252 was broken. ISO-8859-15 had the same problem. Also in this patch is a fix to merge.rb (unused, but it should at least contain no errors), and a unit test for ticket:88. r1293@bean: ser | 2007-07-25 08:19:37 -0400 r1281@bean: ser | 2007-07-24 11:08:48 -0400 Addresses ticket:85 This is a major rewrite of the XML formatting code. The XML writers have all been extracted out of the classes and put into their own class containers. This makes writing parsers easier, and cleaner. There are three formatters, which correspond to the previous three XML writing modes: REXML::Formatters::Default Prints the XML document exactly as it was parsed REXML::Formatters::Pretty Pretty prints the XML document, destroying whitespace in the document REXML::Formatters::Transitive Pretty prints the XML document, preserving whitespace All of the write() functions have been deprecated (some are still used, but these will also go away) except the write() function on Document, which is left for convenience. To pretty print an XML document the canonical way: formatter = REXML::Formatters::Pretty.new( 5 ) # indent by 5 spaces formatter.write( document, output ) r1294@bean: ser | 2007-07-25 08:19:38 -0400 r1283@bean: ser | 2007-07-24 19:53:30 -0400 This goes with the previous commit. r1295@bean: ser | 2007-07-25 08:19:39 -0400 r1285@bean: ser | 2007-07-24 20:02:07 -0400 And THIS goes with the previous two patches. Dammit. r1296@bean: ser | 2007-07-25 08:19:40 -0400 r1287@bean: ser | 2007-07-24 20:12:25 -0400 Applied patch from Jeff Barczewski. Note that this changes what the values of the name and IDs are from the previous behavior -- the values no longer include the quotes. This is the correct behavior, so I'm leaving it in, but it is not backwards compatible. Also fixes the serializer so that it outputs the doctype in a correct format (needed as a result of this change). r1297@bean: ser | 2007-07-25 08:38:38 -0400 Version update git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@12844 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
2007-07-25 12:47:23 +00:00
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 << '&#164;'
when 0xA6; array_enc << '&#166;'
when 0xA8; array_enc << '&#168;'
when 0xB4; array_enc << '&#180;'
when 0xB8; array_enc << '&#184;'
when 0xBC; array_enc << '&#188;'
when 0xBD; array_enc << '&#189;'
when 0xBE; array_enc << '&#190;'
# 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